Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4648 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.8974. Min Act: -0.1700
Data Index: 8678389 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.8349. Min Act: -0.1700
Data Index: 7629301 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.8037. Min Act: -0.1700
Data Index: 8005485 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.7412. Min Act: -0.1700
Data Index: 2484139 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.7099. Min Act: -0.1700
Data Index: 298722 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.7099. Min Act: -0.1700
Data Index: 4442072 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.7099. Min Act: -0.1700
Data Index: 6893906 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6787. Min Act: -0.1700
Data Index: 812597 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6787. Min Act: -0.1700
Data Index: 1886892 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6787. Min Act: -0.1700
Data Index: 8241907 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6787. Min Act: -0.1700
Data Index: 126352 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.7099. Min Act: -0.1700
Data Index: 1581808 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6474. Min Act: -0.1700
Data Index: 3200787 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6474. Min Act: -0.1700
Data Index: 3408621 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6161. Min Act: -0.1700
Data Index: 1689216 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6161. Min Act: -0.1698
Data Index: 823254 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6161. Min Act: -0.1700
Data Index: 7529940 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6474. Min Act: -0.1700
Data Index: 1962184 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6161. Min Act: -0.1700
Data Index: 3380527 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8974. Min Range: -4.8974
Max Act: 4.6161. Min Act: -0.1700
Data Index: 5977093 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19