Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7356466 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7637111 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0938. Min Act: -0.1700
Data Index: 326753 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0626. Min Act: -0.1700
Data Index: 7178766 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0626. Min Act: -0.1700
Data Index: 148704 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4753540 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0313. Min Act: -0.1700
Data Index: 4418099 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0001. Min Act: -0.1699
Data Index: 8377097 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 191098 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8128232 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8420728 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0938. Min Range: -6.0938
Max Act: 6.0313. Min Act: -0.1700
Data Index: 271426 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1699
Data Index: 7698151 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 1258731 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 8537191 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 6044303 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9688. Min Act: -0.1700
Data Index: 6402339 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9376. Min Act: -0.1699
Data Index: 4985599 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9376. Min Act: -0.1700
Data Index: 1864559 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0938. Min Range: -6.0938
Max Act: 5.9376. Min Act: -0.1700
Data Index: 936436 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19