Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5767 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.8169. Min Act: -0.1700
Data Index: 4053981 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.7544. Min Act: -0.1700
Data Index: 285622 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.7232. Min Act: -0.1700
Data Index: 6880698 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6919. Min Act: -0.1700
Data Index: 3036714 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6607. Min Act: -0.1700
Data Index: 779459 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6607. Min Act: -0.1700
Data Index: 6349411 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6607. Min Act: -0.1700
Data Index: 2990049 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6294. Min Act: -0.1700
Data Index: 2078042 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6294. Min Act: -0.1700
Data Index: 4762639 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.6294. Min Act: -0.1700
Data Index: 4099694 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5982. Min Act: -0.1700
Data Index: 80733 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5669. Min Act: -0.1700
Data Index: 761184 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5669. Min Act: -0.1700
Data Index: 7479475 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5669. Min Act: -0.1700
Data Index: 1992294 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5669. Min Act: -0.1700
Data Index: 3600784 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5357. Min Act: -0.1700
Data Index: 1429204 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5357. Min Act: -0.1700
Data Index: 4196646 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5357. Min Act: -0.1700
Data Index: 1294510 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5357. Min Act: -0.1700
Data Index: 4016707 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8169. Min Range: -5.8169
Max Act: 5.5044. Min Act: -0.1700
Data Index: 3343073 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19