Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.8495. Min Act: -0.1700
Data Index: 442851 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.8182. Min Act: -0.1700
Data Index: 935727 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.6932. Min Act: -0.1700
Data Index: 2597421 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.5370. Min Act: -0.1700
Data Index: 3170166 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.5370. Min Act: -0.1700
Data Index: 2731938 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.5057. Min Act: -0.1700
Data Index: 173251 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4745. Min Act: -0.1700
Data Index: 6834145 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4745. Min Act: -0.1700
Data Index: 1216776 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4745. Min Act: -0.1700
Data Index: 138949 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4745. Min Act: -0.1700
Data Index: 5398577 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4432. Min Act: -0.1700
Data Index: 627205 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4432. Min Act: -0.1700
Data Index: 1036291 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4432. Min Act: -0.1700
Data Index: 5398660 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4120. Min Act: -0.1700
Data Index: 3829673 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4120. Min Act: -0.1700
Data Index: 276710 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4432. Min Act: -0.1700
Data Index: 7422827 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4120. Min Act: -0.1700
Data Index: 4649037 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.4120. Min Act: -0.1700
Data Index: 8725663 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.3807. Min Act: -0.1700
Data Index: 2722459 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8495. Min Range: -5.8495
Max Act: 5.3807. Min Act: -0.1700
Data Index: 7901844 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19