Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.3293. Min Act: -0.1700
Data Index: 3022195 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.3136. Min Act: -0.1700
Data Index: 2778739 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.2665. Min Act: -0.1700
Data Index: 5977336 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.2665. Min Act: -0.1700
Data Index: 4612889 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.2194. Min Act: -0.1700
Data Index: 7938786 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.2037. Min Act: -0.1700
Data Index: 3525724 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.2037. Min Act: -0.1700
Data Index: 1179666 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1407. Min Act: -0.1700
Data Index: 6097914 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1879. Min Act: -0.1700
Data Index: 1073272 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1722. Min Act: -0.1700
Data Index: 4466314 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1407. Min Act: -0.1700
Data Index: 8588170 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1565. Min Act: -0.1700
Data Index: 829352 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1250. Min Act: -0.1700
Data Index: 1008936 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1250. Min Act: -0.1700
Data Index: 5016529 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1092. Min Act: -0.1700
Data Index: 3825678 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1250. Min Act: -0.1700
Data Index: 6698753 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.0935. Min Act: -0.1700
Data Index: 4100831 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.0935. Min Act: -0.1700
Data Index: 6021104 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1092. Min Act: -0.1700
Data Index: 2132826 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3293. Min Range: -3.3293
Max Act: 3.1250. Min Act: -0.1700
Data Index: 7324557 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19