Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.1292. Min Act: -0.1700
Data Index: 1199485 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.1605. Min Act: -0.1700
Data Index: 337808 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.1292. Min Act: -0.1700
Data Index: 4740983 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.0980. Min Act: -0.1700
Data Index: 2801542 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.0980. Min Act: -0.1700
Data Index: 6201228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.0980. Min Act: -0.1700
Data Index: 6099843 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.0667. Min Act: -0.1700
Data Index: 4912236 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1605. Min Range: -6.1605
Max Act: 6.0042. Min Act: -0.1700
Data Index: 1441051 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.9730. Min Act: -0.1700
Data Index: 7564266 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.9417. Min Act: -0.1700
Data Index: 6336756 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.9105. Min Act: -0.1700
Data Index: 6201233 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.9105. Min Act: -0.1700
Data Index: 8465575 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.9105. Min Act: -0.1700
Data Index: 3547285 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.8792. Min Act: -0.1700
Data Index: 4740979 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.8480. Min Act: -0.1700
Data Index: 6201224 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.8480. Min Act: -0.1700
Data Index: 5855630 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 599619 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6538489 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4725914 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1605. Min Range: -6.1605
Max Act: 5.8167. Min Act: -0.1700
Data Index: 2925702 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19