Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.5442. Min Act: -0.1700
Data Index: 3820176 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.4504. Min Act: -0.1700
Data Index: 2428283 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.3254. Min Act: -0.1700
Data Index: 23301 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7707473 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2629. Min Act: -0.1700
Data Index: 1469647 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2629. Min Act: -0.1700
Data Index: 3302725 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2317. Min Act: -0.1700
Data Index: 1836787 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2004. Min Act: -0.1700
Data Index: 7969395 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2004. Min Act: -0.1700
Data Index: 8015251 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2004. Min Act: -0.1700
Data Index: 8072801 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2004. Min Act: -0.1700
Data Index: 7423394 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 6780952 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4578734 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 4848530 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 2277241 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 5880674 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 1438047 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.2004. Min Act: -0.1700
Data Index: 7352537 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1692. Min Act: -0.1700
Data Index: 1723897 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5442. Min Range: -5.5442
Max Act: 5.1379. Min Act: -0.1700
Data Index: 476991 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19