Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.9844. Min Act: -0.1700
Data Index: 333686 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.9844. Min Act: -0.1700
Data Index: 8482408 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.8594. Min Act: -0.1700
Data Index: 5287577 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.7032. Min Act: -0.1700
Data Index: 3402153 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.6094. Min Act: -0.1700
Data Index: 611357 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.5782. Min Act: -0.1700
Data Index: 5893452 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.5782. Min Act: -0.1700
Data Index: 6620037 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.5782. Min Act: -0.1700
Data Index: 466376 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.5157. Min Act: -0.1700
Data Index: 2131177 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.5157. Min Act: -0.1700
Data Index: 7907676 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4844. Min Act: -0.1700
Data Index: 3543202 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4844. Min Act: -0.1700
Data Index: 5639002 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4844. Min Act: -0.1700
Data Index: 4043166 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4532. Min Act: -0.1700
Data Index: 7152338 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4219. Min Act: -0.1700
Data Index: 6950142 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4219. Min Act: -0.1700
Data Index: 4672796 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.3907. Min Act: -0.1700
Data Index: 7229210 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.4219. Min Act: -0.1700
Data Index: 7809815 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.3907. Min Act: -0.1700
Data Index: 3297084 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9844. Min Range: -7.9844
Max Act: 7.3907. Min Act: -0.1700
Data Index: 5908840 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19