Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0691. Min Range: -6.0691
Max Act: 6.0691. Min Act: -0.1700
Data Index: 3588468 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0691. Min Range: -6.0691
Max Act: 6.0066. Min Act: -0.1700
Data Index: 224880 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.9129. Min Act: -0.1700
Data Index: 7200187 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.9129. Min Act: -0.1700
Data Index: 7282431 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.9129. Min Act: -0.1700
Data Index: 3111126 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8816. Min Act: -0.1700
Data Index: 2795178 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8816. Min Act: -0.1700
Data Index: 3163474 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8504. Min Act: -0.1700
Data Index: 6517270 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8504. Min Act: -0.1700
Data Index: 6551933 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8504. Min Act: -0.1700
Data Index: 1890775 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8191. Min Act: -0.1700
Data Index: 5976636 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8191. Min Act: -0.1700
Data Index: 2188086 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8504. Min Act: -0.1700
Data Index: 4204002 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7879. Min Act: -0.1700
Data Index: 2495478 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.8191. Min Act: -0.1700
Data Index: 4040559 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7879. Min Act: -0.1700
Data Index: 815357 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7879. Min Act: -0.1700
Data Index: 4329557 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7879. Min Act: -0.1700
Data Index: 7479417 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7879. Min Act: -0.1700
Data Index: 1275545 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0691. Min Range: -6.0691
Max Act: 5.7566. Min Act: -0.1700
Data Index: 4371556 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19