Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.4178. Min Act: -0.1700
Data Index: 8768968 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.4178. Min Act: -0.1700
Data Index: 567224 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.3553. Min Act: -0.1700
Data Index: 7863738 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 5082528 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 6489570 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 811280 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.2303. Min Act: -0.1700
Data Index: 2620830 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1991. Min Act: -0.1700
Data Index: 8774001 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1991. Min Act: -0.1700
Data Index: 6573224 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 6193638 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 3510484 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1293121 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1991. Min Act: -0.1700
Data Index: 8200860 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 6508169 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1366. Min Act: -0.1700
Data Index: 6755823 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1366. Min Act: -0.1700
Data Index: 5935793 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1678. Min Act: -0.1700
Data Index: 1341647 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1053. Min Act: -0.1700
Data Index: 840263 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1053. Min Act: -0.1700
Data Index: 716419 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4178. Min Range: -4.4178
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1994385 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19