Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2216. Min Range: -5.2216
Max Act: 5.2216. Min Act: -0.1700
Data Index: 3576062 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.9716. Min Act: -0.1700
Data Index: 135661 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.9091. Min Act: -0.1700
Data Index: 5384998 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.8466. Min Act: -0.1700
Data Index: 7418217 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.8466. Min Act: -0.1700
Data Index: 2091100 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.8466. Min Act: -0.1700
Data Index: 7976390 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.7528. Min Act: -0.1700
Data Index: 6685508 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.7216. Min Act: -0.1700
Data Index: 4387350 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6903. Min Act: -0.1700
Data Index: 1473779 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6591. Min Act: -0.1700
Data Index: 2503392 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6591. Min Act: -0.1700
Data Index: 359630 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6278. Min Act: -0.1700
Data Index: 5390917 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6278. Min Act: -0.1700
Data Index: 1980641 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6591. Min Act: -0.1700
Data Index: 50798 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6278. Min Act: -0.1700
Data Index: 3386901 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6278. Min Act: -0.1700
Data Index: 7706695 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.6278. Min Act: -0.1700
Data Index: 2467648 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.5966. Min Act: -0.1700
Data Index: 2960495 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.5966. Min Act: -0.1700
Data Index: 3287019 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2216. Min Range: -5.2216
Max Act: 4.5966. Min Act: -0.1700
Data Index: 2935127 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19