Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 398 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.3157. Min Act: -0.1700
Data Index: 4404329 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.2532. Min Act: -0.1700
Data Index: 7918519 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.1907. Min Act: -0.1700
Data Index: 3283996 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.0969. Min Act: -0.1700
Data Index: 5927644 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.0344. Min Act: -0.1700
Data Index: 5718072 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3157. Min Range: -6.3157
Max Act: 6.0032. Min Act: -0.1700
Data Index: 5433474 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9719. Min Act: -0.1700
Data Index: 1762246 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9407. Min Act: -0.1700
Data Index: 4369179 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9094. Min Act: -0.1700
Data Index: 8668407 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9407. Min Act: -0.1700
Data Index: 6401686 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9094. Min Act: -0.1700
Data Index: 4753932 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9094. Min Act: -0.1700
Data Index: 4293071 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.9094. Min Act: -0.1700
Data Index: 7793695 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8782. Min Act: -0.1700
Data Index: 7167114 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8782. Min Act: -0.1700
Data Index: 5146822 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8782. Min Act: -0.1700
Data Index: 4842870 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8782. Min Act: -0.1700
Data Index: 7522627 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8469. Min Act: -0.1700
Data Index: 7459790 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8469. Min Act: -0.1700
Data Index: 5325971 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3157. Min Range: -6.3157
Max Act: 5.8469. Min Act: -0.1700
Data Index: 6442818 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19