Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.5903. Min Act: -0.1700
Data Index: 1259041 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.5591. Min Act: -0.1700
Data Index: 7889447 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.4966. Min Act: -0.1700
Data Index: 5400949 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.3403. Min Act: -0.1700
Data Index: 1734852 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.3091. Min Act: -0.1700
Data Index: 5050948 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.3091. Min Act: -0.1700
Data Index: 4412003 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.2778. Min Act: -0.1700
Data Index: 8587786 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.2778. Min Act: -0.1700
Data Index: 6449567 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.2466. Min Act: -0.1700
Data Index: 2006890 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.2466. Min Act: -0.1700
Data Index: 5779229 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.2153. Min Act: -0.1700
Data Index: 4857838 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1841. Min Act: -0.1700
Data Index: 2137516 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1841. Min Act: -0.1700
Data Index: 1432704 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1841. Min Act: -0.1700
Data Index: 4626465 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1528. Min Act: -0.1700
Data Index: 3108545 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1841. Min Act: -0.1700
Data Index: 7384996 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1528. Min Act: -0.1700
Data Index: 8123866 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1528. Min Act: -0.1700
Data Index: 880383 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.1216. Min Act: -0.1700
Data Index: 6679976 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5903. Min Range: -4.5903
Max Act: 4.0590. Min Act: -0.1700
Data Index: 3094539 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19