Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2220. Min Range: -6.2220
Max Act: 6.2220. Min Act: -0.1700
Data Index: 413010 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2220. Min Range: -6.2220
Max Act: 6.1595. Min Act: -0.1700
Data Index: 5367727 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2220. Min Range: -6.2220
Max Act: 6.1282. Min Act: -0.1700
Data Index: 4455352 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2220. Min Range: -6.2220
Max Act: 6.0657. Min Act: -0.1700
Data Index: 7680895 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2220. Min Range: -6.2220
Max Act: 6.0345. Min Act: -0.1700
Data Index: 7411109 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.9407. Min Act: -0.1700
Data Index: 4442645 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.9095. Min Act: -0.1700
Data Index: 3100096 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.9407. Min Act: -0.1700
Data Index: 869856 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.9407. Min Act: -0.1700
Data Index: 2920158 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.9095. Min Act: -0.1700
Data Index: 3140953 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.8782. Min Act: -0.1700
Data Index: 984653 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.8470. Min Act: -0.1700
Data Index: 8642232 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.8470. Min Act: -0.1700
Data Index: 788097 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.8157. Min Act: -0.1700
Data Index: 4485510 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.8157. Min Act: -0.1700
Data Index: 4477252 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.7845. Min Act: -0.1700
Data Index: 8546282 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.7532. Min Act: -0.1700
Data Index: 3432803 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.7845. Min Act: -0.1700
Data Index: 3626140 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.7845. Min Act: -0.1700
Data Index: 7929147 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2220. Min Range: -6.2220
Max Act: 5.7845. Min Act: -0.1700
Data Index: 2250994 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19