Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0398. Min Range: -6.0398
Max Act: 6.0398. Min Act: -0.1700
Data Index: 8392466 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.9148. Min Act: -0.1700
Data Index: 3497566 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.8523. Min Act: -0.1700
Data Index: 5186103 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.8211. Min Act: -0.1700
Data Index: 7879247 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.8211. Min Act: -0.1700
Data Index: 3889873 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.7586. Min Act: -0.1700
Data Index: 7529862 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.7898. Min Act: -0.1700
Data Index: 5261176 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.7273. Min Act: -0.1700
Data Index: 627040 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.7586. Min Act: -0.1700
Data Index: 5503017 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 2572292 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 797292 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 4090404 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 5236378 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 5741937 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6961. Min Act: -0.1700
Data Index: 48978 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6648. Min Act: -0.1700
Data Index: 5844283 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6648. Min Act: -0.1700
Data Index: 7714125 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6336. Min Act: -0.1700
Data Index: 1272538 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6023. Min Act: -0.1700
Data Index: 5798057 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0398. Min Range: -6.0398
Max Act: 5.6023. Min Act: -0.1700
Data Index: 7301753 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19