Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2577 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.7840. Min Act: -0.1700
Data Index: 1464325 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.6277. Min Act: -0.1700
Data Index: 3814514 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5340. Min Act: -0.1700
Data Index: 408905 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5027. Min Act: -0.1700
Data Index: 5144118 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3454539 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3481134 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4715. Min Act: -0.1700
Data Index: 3065167 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4402. Min Act: -0.1700
Data Index: 1914949 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4715. Min Act: -0.1700
Data Index: 3064122 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 2832040 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1575351 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3777. Min Act: -0.1700
Data Index: 1959117 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1006260 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.4090. Min Act: -0.1700
Data Index: 2851006 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3777. Min Act: -0.1700
Data Index: 7466625 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3777. Min Act: -0.1700
Data Index: 3023587 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3465. Min Act: -0.1700
Data Index: 595521 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3777. Min Act: -0.1700
Data Index: 5471211 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2235042 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7840. Min Range: -5.7840
Max Act: 5.3152. Min Act: -0.1700
Data Index: 2510788 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19