Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1148. Min Range: -8.1148
Max Act: 8.1148. Min Act: -0.1700
Data Index: 849618 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.9585. Min Act: -0.1700
Data Index: 7710227 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.7085. Min Act: -0.1700
Data Index: 4587597 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.6773. Min Act: -0.1700
Data Index: 4538936 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.6460. Min Act: -0.1700
Data Index: 38123 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.6460. Min Act: -0.1700
Data Index: 1302368 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.6460. Min Act: -0.1700
Data Index: 2557150 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.5210. Min Act: -0.1700
Data Index: 7199972 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.5210. Min Act: -0.1700
Data Index: 4618137 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.4898. Min Act: -0.1700
Data Index: 4569884 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3960. Min Act: -0.1700
Data Index: 207558 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.4273. Min Act: -0.1700
Data Index: 2742041 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3648. Min Act: -0.1700
Data Index: 7696668 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3648. Min Act: -0.1700
Data Index: 8130281 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3648. Min Act: -0.1700
Data Index: 3056622 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3648. Min Act: -0.1700
Data Index: 2965434 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3335. Min Act: -0.1700
Data Index: 2007768 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3335. Min Act: -0.1700
Data Index: 6080720 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3335. Min Act: -0.1700
Data Index: 6884575 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1148. Min Range: -8.1148
Max Act: 7.3335. Min Act: -0.1700
Data Index: 6958247 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19