Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.9864. Min Act: -0.1700
Data Index: 2194263 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.9551. Min Act: -0.1700
Data Index: 4647659 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.8614. Min Act: -0.1700
Data Index: 7018955 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.8301. Min Act: -0.1700
Data Index: 7662934 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7364. Min Act: -0.1700
Data Index: 5497450 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5497449 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.7051. Min Act: -0.1700
Data Index: 8787149 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3388485 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 1578319 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3407250 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.6426. Min Act: -0.1700
Data Index: 3494029 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5801. Min Act: -0.1700
Data Index: 6850599 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5801. Min Act: -0.1700
Data Index: 3177722 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5801. Min Act: -0.1700
Data Index: 196042 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5801. Min Act: -0.1700
Data Index: 5338792 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5489. Min Act: -0.1700
Data Index: 4052541 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5176. Min Act: -0.1700
Data Index: 2701672 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5489. Min Act: -0.1700
Data Index: 8787147 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5489. Min Act: -0.1700
Data Index: 3503464 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9864. Min Range: -4.9864
Max Act: 4.5176. Min Act: -0.1700
Data Index: 7902479 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19