Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.5884. Min Act: -0.1700
Data Index: 8795832 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.4947. Min Act: -0.1700
Data Index: 637218 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.4322. Min Act: -0.1700
Data Index: 6970590 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.2134. Min Act: -0.1700
Data Index: 7747033 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.1197. Min Act: -0.1700
Data Index: 8795573 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.0884. Min Act: -0.1700
Data Index: 2289690 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.0259. Min Act: -0.1700
Data Index: 2802499 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5884. Min Range: -7.5884
Max Act: 7.0259. Min Act: -0.1700
Data Index: 1545595 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 973411 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 7322056 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 2437610 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 4768383 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9634. Min Act: -0.1700
Data Index: 4641735 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9322. Min Act: -0.1700
Data Index: 3894014 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9322. Min Act: -0.1700
Data Index: 7864294 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.9009. Min Act: -0.1700
Data Index: 7920006 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.8697. Min Act: -0.1700
Data Index: 4531844 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.8697. Min Act: -0.1700
Data Index: 1685407 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.8697. Min Act: -0.1700
Data Index: 2398417 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5884. Min Range: -7.5884
Max Act: 6.8384. Min Act: -0.1700
Data Index: 7494407 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19