Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.6515. Min Act: -0.1700
Data Index: 8613269 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.5577. Min Act: -0.1700
Data Index: 8159732 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.5265. Min Act: -0.1700
Data Index: 4641884 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.4327. Min Act: -0.1700
Data Index: 683257 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3702. Min Act: -0.1700
Data Index: 1770125 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3390. Min Act: -0.1700
Data Index: 6722517 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3390. Min Act: -0.1700
Data Index: 5364823 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3390. Min Act: -0.1700
Data Index: 8720695 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3390. Min Act: -0.1700
Data Index: 3779482 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3390. Min Act: -0.1700
Data Index: 7448609 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.3077. Min Act: -0.1700
Data Index: 2344296 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.2452. Min Act: -0.1700
Data Index: 5099876 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.2140. Min Act: -0.1700
Data Index: 8175517 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.2140. Min Act: -0.1700
Data Index: 8655498 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.2140. Min Act: -0.1700
Data Index: 2033175 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.1827. Min Act: -0.1700
Data Index: 4588911 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.1827. Min Act: -0.1700
Data Index: 4330123 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.1202. Min Act: -0.1700
Data Index: 1065816 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.1202. Min Act: -0.1700
Data Index: 8539979 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6515. Min Range: -6.6515
Max Act: 6.1202. Min Act: -0.1700
Data Index: 2920927 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19