Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1343. Min Range: -9.1343
Max Act: 9.1343. Min Act: -0.1700
Data Index: 6149990 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1343. Min Range: -9.1343
Max Act: 9.0718. Min Act: -0.1700
Data Index: 379771 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.9468. Min Act: -0.1700
Data Index: 191543 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.9468. Min Act: -0.1700
Data Index: 6244131 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8843. Min Act: -0.1700
Data Index: 3754250 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8843. Min Act: -0.1700
Data Index: 2271494 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8843. Min Act: -0.1700
Data Index: 8066095 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8218. Min Act: -0.1700
Data Index: 5114763 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8218. Min Act: -0.1700
Data Index: 2185097 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8218. Min Act: -0.1700
Data Index: 4146250 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.8843. Min Act: -0.1700
Data Index: 3988444 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.7593. Min Act: -0.1700
Data Index: 2897508 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.7593. Min Act: -0.1700
Data Index: 379761 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 7888834 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 7667834 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 6839741 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 379766 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 3642641 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6968. Min Act: -0.1700
Data Index: 2244771 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1343. Min Range: -9.1343
Max Act: 8.6343. Min Act: -0.1700
Data Index: 650332 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19