Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1534. Min Range: -7.1534
Max Act: 7.1534. Min Act: -0.1700
Data Index: 1189127 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1534. Min Range: -7.1534
Max Act: 7.1222. Min Act: -0.1700
Data Index: 4187000 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1534. Min Range: -7.1534
Max Act: 7.1222. Min Act: -0.1700
Data Index: 6282767 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1534. Min Range: -7.1534
Max Act: 7.0909. Min Act: -0.1700
Data Index: 6797934 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1534. Min Range: -7.1534
Max Act: 7.0909. Min Act: -0.1700
Data Index: 613969 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.9972. Min Act: -0.1700
Data Index: 4105675 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.9659. Min Act: -0.1700
Data Index: 3772082 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.9347. Min Act: -0.1700
Data Index: 1115426 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.9034. Min Act: -0.1700
Data Index: 6771318 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.9034. Min Act: -0.1700
Data Index: 4395382 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8722. Min Act: -0.1700
Data Index: 8403258 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8722. Min Act: -0.1700
Data Index: 132189 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8409. Min Act: -0.1700
Data Index: 1360026 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8409. Min Act: -0.1700
Data Index: 4633150 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8409. Min Act: -0.1700
Data Index: 7048407 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.8097. Min Act: -0.1700
Data Index: 1293343 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.7784. Min Act: -0.1700
Data Index: 4441894 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.7784. Min Act: -0.1700
Data Index: 688273 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.7784. Min Act: -0.1700
Data Index: 2191947 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1534. Min Range: -7.1534
Max Act: 6.7784. Min Act: -0.1700
Data Index: 6383155 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19