Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2733. Min Range: -6.2733
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1758453 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2733. Min Range: -6.2733
Max Act: 6.1170. Min Act: -0.1700
Data Index: 3751890 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.9608. Min Act: -0.1700
Data Index: 5113692 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.8983. Min Act: -0.1700
Data Index: 1109824 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.8670. Min Act: -0.1700
Data Index: 7325205 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.8045. Min Act: -0.1700
Data Index: 6258989 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4747416 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.6795. Min Act: -0.1700
Data Index: 5310583 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.7108. Min Act: -0.1700
Data Index: 143806 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.7108. Min Act: -0.1700
Data Index: 3486939 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.6483. Min Act: -0.1700
Data Index: 1153902 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.6170. Min Act: -0.1700
Data Index: 2746770 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.6170. Min Act: -0.1700
Data Index: 7091624 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.6170. Min Act: -0.1700
Data Index: 3363915 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.5545. Min Act: -0.1700
Data Index: 6031266 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.5545. Min Act: -0.1700
Data Index: 2214739 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.5233. Min Act: -0.1700
Data Index: 1197470 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.5233. Min Act: -0.1700
Data Index: 6623750 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.4920. Min Act: -0.1700
Data Index: 252205 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2733. Min Range: -6.2733
Max Act: 5.4920. Min Act: -0.1700
Data Index: 5877523 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19