Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8268. Min Range: -8.8268
Max Act: 8.8268. Min Act: -0.1700
Data Index: 6008944 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.9518. Min Act: -0.1700
Data Index: 1388153 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.9518. Min Act: -0.1700
Data Index: 2826914 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.8893. Min Act: -0.1700
Data Index: 2163268 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.7956. Min Act: -0.1700
Data Index: 7335741 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.7643. Min Act: -0.1700
Data Index: 853497 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.7956. Min Act: -0.1700
Data Index: 6441371 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.7643. Min Act: -0.1700
Data Index: 312158 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.6706. Min Act: -0.1700
Data Index: 5472462 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.6393. Min Act: -0.1700
Data Index: 5657124 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5456. Min Act: -0.1700
Data Index: 8092435 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5143. Min Act: -0.1700
Data Index: 4714080 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5456. Min Act: -0.1700
Data Index: 767736 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5456. Min Act: -0.1700
Data Index: 410793 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5143. Min Act: -0.1700
Data Index: 3933201 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5456. Min Act: -0.1700
Data Index: 1002260 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.4831. Min Act: -0.1700
Data Index: 879041 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.4831. Min Act: -0.1700
Data Index: 8748257 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.5143. Min Act: -0.1700
Data Index: 3994542 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8268. Min Range: -8.8268
Max Act: 7.4518. Min Act: -0.1700
Data Index: 2391636 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19