Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.7064. Min Act: -0.1700
Data Index: 7185490 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.5814. Min Act: -0.1700
Data Index: 7722657 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.5814. Min Act: -0.1700
Data Index: 4919823 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.5814. Min Act: -0.1700
Data Index: 5389415 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.5189. Min Act: -0.1700
Data Index: 6248563 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.4564. Min Act: -0.1700
Data Index: 5867635 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.3314. Min Act: -0.1700
Data Index: 6755463 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.3314. Min Act: -0.1700
Data Index: 3959004 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.2377. Min Act: -0.1700
Data Index: 5030891 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.3002. Min Act: -0.1700
Data Index: 8076595 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.2064. Min Act: -0.1700
Data Index: 8467908 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1752. Min Act: -0.1700
Data Index: 1748944 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1439. Min Act: -0.1700
Data Index: 2084896 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1439. Min Act: -0.1700
Data Index: 6130 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1127. Min Act: -0.1700
Data Index: 3457171 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1127. Min Act: -0.1700
Data Index: 8356541 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.0814. Min Act: -0.1700
Data Index: 520458 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.0814. Min Act: -0.1700
Data Index: 7225050 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.1127. Min Act: -0.1700
Data Index: 1445370 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7064. Min Range: -6.7064
Max Act: 6.0502. Min Act: -0.1700
Data Index: 4529921 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19