Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5859 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.8536. Min Act: -0.1700
Data Index: 3440886 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.7598. Min Act: -0.1700
Data Index: 6526967 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.7286. Min Act: -0.1700
Data Index: 8373025 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.6661. Min Act: -0.1700
Data Index: 7511676 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.6348. Min Act: -0.1700
Data Index: 832679 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.5723. Min Act: -0.1700
Data Index: 1353578 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.5411. Min Act: -0.1700
Data Index: 8094918 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.5098. Min Act: -0.1700
Data Index: 810712 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.5098. Min Act: -0.1700
Data Index: 1167365 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4786. Min Act: -0.1700
Data Index: 7299321 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4786. Min Act: -0.1700
Data Index: 1527259 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4473. Min Act: -0.1700
Data Index: 5842925 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4473. Min Act: -0.1700
Data Index: 2618834 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4473. Min Act: -0.1700
Data Index: 7374503 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4161. Min Act: -0.1700
Data Index: 4794698 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4161. Min Act: -0.1700
Data Index: 1575670 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.4161. Min Act: -0.1700
Data Index: 2505725 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.3848. Min Act: -0.1700
Data Index: 2067975 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.3536. Min Act: -0.1700
Data Index: 865323 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8536. Min Range: -6.8536
Max Act: 6.3536. Min Act: -0.1700
Data Index: 6960100 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19