Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 976 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3960. Min Act: -0.1700
Data Index: 2196787 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3960. Min Act: -0.1700
Data Index: 2724690 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3803. Min Act: -0.1700
Data Index: 3993895 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3489. Min Act: -0.1700
Data Index: 5379878 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3332. Min Act: -0.1700
Data Index: 3546197 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3175. Min Act: -0.1700
Data Index: 6224652 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3018. Min Act: -0.1700
Data Index: 3993896 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.3018. Min Act: -0.1700
Data Index: 4096604 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2704. Min Act: -0.1700
Data Index: 6274161 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2390. Min Act: -0.1700
Data Index: 5338406 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2547. Min Act: -0.1700
Data Index: 3234849 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2547. Min Act: -0.1700
Data Index: 6540850 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2390. Min Act: -0.1700
Data Index: 7206339 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2390. Min Act: -0.1700
Data Index: 6211680 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2233. Min Act: -0.1700
Data Index: 3553053 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2233. Min Act: -0.1700
Data Index: 3886864 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.2076. Min Act: -0.1700
Data Index: 8666678 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1918. Min Act: -0.1700
Data Index: 7218723 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1918. Min Act: -0.1700
Data Index: 3633546 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3960. Min Range: -3.3960
Max Act: 3.1761. Min Act: -0.1700
Data Index: 1033272 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19