Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0926. Min Range: -6.0926
Max Act: 6.0926. Min Act: -0.1700
Data Index: 1628469 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0926. Min Range: -6.0926
Max Act: 6.0926. Min Act: -0.1700
Data Index: 3252162 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0926. Min Range: -6.0926
Max Act: 6.0614. Min Act: -0.1700
Data Index: 5307129 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0926. Min Range: -6.0926
Max Act: 6.0301. Min Act: -0.1700
Data Index: 864618 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.9676. Min Act: -0.1700
Data Index: 836133 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3326627 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.9051. Min Act: -0.1700
Data Index: 5009508 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.9051. Min Act: -0.1700
Data Index: 2912599 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8739. Min Act: -0.1700
Data Index: 4895375 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8739. Min Act: -0.1699
Data Index: 8423063 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8426. Min Act: -0.1700
Data Index: 1990367 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8426. Min Act: -0.1700
Data Index: 5951635 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8114. Min Act: -0.1700
Data Index: 3280674 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.8114. Min Act: -0.1700
Data Index: 136793 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7489. Min Act: -0.1700
Data Index: 5539241 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7489. Min Act: -0.1700
Data Index: 2081033 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7489. Min Act: -0.1700
Data Index: 2849905 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4377560 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7176. Min Act: -0.1700
Data Index: 4179236 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.7176. Min Act: -0.1700
Data Index: 2533483 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19