Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5391 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4910. Min Act: -0.1700
Data Index: 7536221 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4747. Min Act: -0.1700
Data Index: 3478692 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4910. Min Act: -0.1700
Data Index: 4787758 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4585. Min Act: -0.1700
Data Index: 7427670 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4422. Min Act: -0.1700
Data Index: 6660182 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4260. Min Act: -0.1700
Data Index: 6336243 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4422. Min Act: -0.1700
Data Index: 7433886 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.4097. Min Act: -0.1700
Data Index: 7641786 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3933. Min Act: -0.1700
Data Index: 3743469 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3933. Min Act: -0.1700
Data Index: 1149216 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3933. Min Act: -0.1700
Data Index: 2911402 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3933. Min Act: -0.1700
Data Index: 3496408 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3933. Min Act: -0.1700
Data Index: 4121744 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3770. Min Act: -0.1700
Data Index: 6899477 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3770. Min Act: -0.1700
Data Index: 8551314 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3770. Min Act: -0.1700
Data Index: 1820549 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3770. Min Act: -0.1700
Data Index: 2568799 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3770. Min Act: -0.1700
Data Index: 4914118 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3606. Min Act: -0.1700
Data Index: 818328 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4910. Min Range: -2.4910
Max Act: 2.3606. Min Act: -0.1700
Data Index: 638335 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19