Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.9925. Min Act: -0.1700
Data Index: 8087192 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.5863. Min Act: -0.1700
Data Index: 7344449 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.5863. Min Act: -0.1700
Data Index: 419863 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4925. Min Act: -0.1700
Data Index: 7998328 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4925. Min Act: -0.1700
Data Index: 6074439 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4925. Min Act: -0.1700
Data Index: 5790639 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4613. Min Act: -0.1700
Data Index: 5492662 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4613. Min Act: -0.1700
Data Index: 4938328 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4300. Min Act: -0.1700
Data Index: 1379677 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4300. Min Act: -0.1700
Data Index: 735108 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4300. Min Act: -0.1700
Data Index: 89607 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.4300. Min Act: -0.1700
Data Index: 3527651 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3988. Min Act: -0.1700
Data Index: 39415 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3988. Min Act: -0.1700
Data Index: 4419645 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3675. Min Act: -0.1700
Data Index: 932606 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3675. Min Act: -0.1700
Data Index: 3576388 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3363. Min Act: -0.1700
Data Index: 8085784 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3050. Min Act: -0.1700
Data Index: 8007133 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3050. Min Act: -0.1700
Data Index: 3129292 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9925. Min Range: -6.9925
Max Act: 6.3050. Min Act: -0.1700
Data Index: 5847685 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19