Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1582 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.6343. Min Act: -0.1700
Data Index: 5387518 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.6030. Min Act: -0.1700
Data Index: 4814564 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5560. Min Act: -0.1700
Data Index: 398201 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5717. Min Act: -0.1700
Data Index: 1081786 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5404. Min Act: -0.1700
Data Index: 7271453 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5717. Min Act: -0.1700
Data Index: 2716768 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5247. Min Act: -0.1700
Data Index: 6509150 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.5091. Min Act: -0.1700
Data Index: 2826104 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.4464. Min Act: -0.1700
Data Index: 1038854 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.4151. Min Act: -0.1700
Data Index: 2594663 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3837. Min Act: -0.1700
Data Index: 5757488 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3680. Min Act: -0.1700
Data Index: 2821299 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3680. Min Act: -0.1700
Data Index: 2967099 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3523. Min Act: -0.1700
Data Index: 1069945 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3366. Min Act: -0.1700
Data Index: 8700307 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3366. Min Act: -0.1700
Data Index: 7475705 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3366. Min Act: -0.1700
Data Index: 1278452 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3366. Min Act: -0.1700
Data Index: 8019297 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3053. Min Act: -0.1700
Data Index: 6531849 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6343. Min Range: -3.6343
Max Act: 3.3053. Min Act: -0.1700
Data Index: 1211935 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19