Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3963 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0845. Min Act: -0.1700
Data Index: 4015100 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0845. Min Act: -0.1700
Data Index: 4742644 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0845. Min Act: -0.1700
Data Index: 4742665 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0220. Min Act: -0.1700
Data Index: 78192 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0220. Min Act: -0.1700
Data Index: 1028854 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0220. Min Act: -0.1700
Data Index: 8257216 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0220. Min Act: -0.1700
Data Index: 7155353 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.9595. Min Act: -0.1700
Data Index: 3099342 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.9595. Min Act: -0.1700
Data Index: 6995193 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.9595. Min Act: -0.1700
Data Index: 3377970 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.9595. Min Act: -0.1700
Data Index: 373458 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0845. Min Range: -8.0845
Max Act: 8.0220. Min Act: -0.1700
Data Index: 2997416 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 5801528 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 8257195 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 3099361 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 3108577 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 4415490 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8970. Min Act: -0.1700
Data Index: 7882765 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8345. Min Act: -0.1700
Data Index: 6651134 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0845. Min Range: -8.0845
Max Act: 7.8345. Min Act: -0.1700
Data Index: 4415503 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19