Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4981 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.6690. Min Act: -0.1700
Data Index: 2600922 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.5440. Min Act: -0.1700
Data Index: 5647577 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.3565. Min Act: -0.1700
Data Index: 7743392 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.2940. Min Act: -0.1700
Data Index: 8270190 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.1690. Min Act: -0.1700
Data Index: 8818128 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.1065. Min Act: -0.1700
Data Index: 8818129 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.6690. Min Range: -13.6690
Max Act: 13.1065. Min Act: -0.1700
Data Index: 5668190 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 6888573 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 7213342 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 7320929 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 5970141 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 5970142 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 7320931 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.9190. Min Act: -0.1700
Data Index: 418408 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.8565. Min Act: -0.1700
Data Index: 2697422 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.7940. Min Act: -0.1700
Data Index: 2775298 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.7940. Min Act: -0.1700
Data Index: 5854569 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.7940. Min Act: -0.1700
Data Index: 1221530 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.7315. Min Act: -0.1700
Data Index: 2917535 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.6690. Min Range: -13.6690
Max Act: 12.7315. Min Act: -0.1700
Data Index: 4881204 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19