Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4044684 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6904. Min Act: -0.1700
Data Index: 734289 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6592. Min Act: -0.1700
Data Index: 3427463 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.6279. Min Act: -0.1700
Data Index: 4941449 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5967. Min Act: -0.1700
Data Index: 6240431 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5967. Min Act: -0.1700
Data Index: 1583857 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 4664996 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5654. Min Act: -0.1700
Data Index: 7834851 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5342. Min Act: -0.1700
Data Index: 7243272 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 4137851 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 399636 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 1338332 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 7462193 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4716. Min Act: -0.1700
Data Index: 3400508 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 2213136 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4716. Min Act: -0.1700
Data Index: 7149127 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.5029. Min Act: -0.1700
Data Index: 8253551 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4404. Min Act: -0.1700
Data Index: 2965691 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4091. Min Act: -0.1700
Data Index: 4407498 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8467. Min Range: -4.8467
Max Act: 4.4091. Min Act: -0.1700
Data Index: 871923 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19