Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3663 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1000. Min Range: -5.1000
Max Act: 5.1000. Min Act: -0.1700
Data Index: 1286563 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1000. Min Range: -5.1000
Max Act: 5.0687. Min Act: -0.1700
Data Index: 1139011 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.7250. Min Act: -0.1700
Data Index: 3451752 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.7250. Min Act: -0.1700
Data Index: 4893165 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6937. Min Act: -0.1700
Data Index: 7533993 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6937. Min Act: -0.1700
Data Index: 3261062 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6312. Min Act: -0.1700
Data Index: 381775 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6312. Min Act: -0.1700
Data Index: 3363472 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6312. Min Act: -0.1700
Data Index: 6318457 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6312. Min Act: -0.1700
Data Index: 5153868 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6312. Min Act: -0.1700
Data Index: 7516281 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 816037 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 994226 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 8012917 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 2369946 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 5993301 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.6000. Min Act: -0.1700
Data Index: 3396660 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5345320 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.5687. Min Act: -0.1700
Data Index: 3335189 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1000. Min Range: -5.1000
Max Act: 4.5687. Min Act: -0.1700
Data Index: 6285163 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19