Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.5404. Min Act: -0.1700
Data Index: 2081311 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.4779. Min Act: -0.1700
Data Index: 7822305 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.3529. Min Act: -0.1700
Data Index: 5268263 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.2904. Min Act: -0.1700
Data Index: 7205949 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.2904. Min Act: -0.1700
Data Index: 4689045 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.2904. Min Act: -0.1700
Data Index: 383228 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.2591. Min Act: -0.1700
Data Index: 1617405 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.1966. Min Act: -0.1700
Data Index: 1145042 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.1341. Min Act: -0.1700
Data Index: 950039 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0716. Min Act: -0.1700
Data Index: 5707160 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0716. Min Act: -0.1700
Data Index: 6548848 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0404. Min Act: -0.1700
Data Index: 2550445 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0716. Min Act: -0.1700
Data Index: 5221569 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0716. Min Act: -0.1700
Data Index: 1891650 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0091. Min Act: -0.1700
Data Index: 2616255 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0091. Min Act: -0.1700
Data Index: 945851 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0404. Min Act: -0.1700
Data Index: 7482588 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0091. Min Act: -0.1700
Data Index: 3987086 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9154. Min Act: -0.1700
Data Index: 7283122 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9466. Min Act: -0.1700
Data Index: 7065667 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19