Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.9227. Min Act: -0.1700
Data Index: 6421085 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.8602. Min Act: -0.1700
Data Index: 3809150 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.7977. Min Act: -0.1700
Data Index: 7831582 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.8290. Min Act: -0.1700
Data Index: 5927430 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.7665. Min Act: -0.1700
Data Index: 6421086 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.7352. Min Act: -0.1700
Data Index: 464067 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.7352. Min Act: -0.1700
Data Index: 2341720 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.7040. Min Act: -0.1700
Data Index: 5281103 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 7213345 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6415. Min Act: -0.1700
Data Index: 362957 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 4789207 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.5790. Min Act: -0.1700
Data Index: 7169709 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 4766565 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 6305991 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 2123757 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.6102. Min Act: -0.1700
Data Index: 2345289 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.5790. Min Act: -0.1700
Data Index: 5227182 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.5477. Min Act: -0.1700
Data Index: 4920990 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.5790. Min Act: -0.1700
Data Index: 6436505 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9227. Min Range: -5.9227
Max Act: 5.5790. Min Act: -0.1700
Data Index: 935087 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19