Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.8492. Min Act: -0.1700
Data Index: 35242 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.7710. Min Act: -0.1700
Data Index: 3548657 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.7554. Min Act: -0.1700
Data Index: 3391589 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.7241. Min Act: -0.1700
Data Index: 2520169 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.7241. Min Act: -0.1700
Data Index: 5286498 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.7085. Min Act: -0.1700
Data Index: 2560140 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6615. Min Act: -0.1700
Data Index: 20431 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6459. Min Act: -0.1700
Data Index: 269277 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6303. Min Act: -0.1700
Data Index: 5725887 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6459. Min Act: -0.1700
Data Index: 4829613 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6146. Min Act: -0.1700
Data Index: 8040643 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.6146. Min Act: -0.1700
Data Index: 4474674 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5990. Min Act: -0.1700
Data Index: 958321 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5990. Min Act: -0.1700
Data Index: 2871284 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5676. Min Act: -0.1700
Data Index: 4742160 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5676. Min Act: -0.1700
Data Index: 1779400 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5520. Min Act: -0.1700
Data Index: 2739683 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5207. Min Act: -0.1700
Data Index: 4999208 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5520. Min Act: -0.1700
Data Index: 4937704 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8492. Min Range: -3.8492
Max Act: 3.5207. Min Act: -0.1700
Data Index: 2926061 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19