Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.9252. Min Act: -0.1700
Data Index: 3619360 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.9252. Min Act: -0.1700
Data Index: 491137 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8939. Min Act: -0.1700
Data Index: 491142 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8939. Min Act: -0.1699
Data Index: 7701807 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8939. Min Act: -0.1700
Data Index: 4400064 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8626. Min Act: -0.1700
Data Index: 4738891 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8314. Min Act: -0.1700
Data Index: 6753906 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8314. Min Act: -0.1700
Data Index: 7733977 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8001. Min Act: -0.1700
Data Index: 8128258 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.8001. Min Act: -0.1700
Data Index: 524664 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1700
Data Index: 4645711 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1699
Data Index: 122300 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1700
Data Index: 4838874 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1700
Data Index: 8595408 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1700
Data Index: 4604226 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7688. Min Act: -0.1700
Data Index: 6753905 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7062. Min Act: -0.1700
Data Index: 4766271 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7375. Min Act: -0.1700
Data Index: 491129 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7375. Min Act: -0.1700
Data Index: 491143 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9252. Min Range: -3.9252
Max Act: 3.7375. Min Act: -0.1697
Data Index: 5016008 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19