Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3131 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.6960. Min Act: -0.1700
Data Index: 4502707 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.6023. Min Act: -0.1700
Data Index: 8395704 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.5710. Min Act: -0.1700
Data Index: 4111502 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.6335. Min Act: -0.1700
Data Index: 8137279 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.5398. Min Act: -0.1700
Data Index: 4502703 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4773. Min Act: -0.1700
Data Index: 3776316 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4773. Min Act: -0.1700
Data Index: 7321639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4460. Min Act: -0.1700
Data Index: 47273 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4460. Min Act: -0.1700
Data Index: 3581335 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4148. Min Act: -0.1700
Data Index: 4940372 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4148. Min Act: -0.1700
Data Index: 6452979 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.4148. Min Act: -0.1700
Data Index: 1293974 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.3523. Min Act: -0.1700
Data Index: 3743382 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.3210. Min Act: -0.1700
Data Index: 6422481 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.3210. Min Act: -0.1700
Data Index: 7565244 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.3210. Min Act: -0.1700
Data Index: 5803244 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.2898. Min Act: -0.1700
Data Index: 6694196 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.2898. Min Act: -0.1700
Data Index: 3134382 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.2898. Min Act: -0.1700
Data Index: 4502713 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6960. Min Range: -6.6960
Max Act: 6.2898. Min Act: -0.1700
Data Index: 5287314 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19