Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3719 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.3490. Min Act: -0.1700
Data Index: 890578 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.2552. Min Act: -0.1700
Data Index: 4226036 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.2240. Min Act: -0.1700
Data Index: 3644363 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 2774264 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 1261428 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 6920904 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 492049 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3794692 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1615. Min Act: -0.1700
Data Index: 8348847 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1302. Min Act: -0.1700
Data Index: 8823558 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1302. Min Act: -0.1700
Data Index: 5375117 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1302. Min Act: -0.1700
Data Index: 3134083 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1302. Min Act: -0.1700
Data Index: 8649198 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6428945 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0990. Min Act: -0.1700
Data Index: 450582 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0677. Min Act: -0.1700
Data Index: 6317965 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2030692 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.1302. Min Act: -0.1700
Data Index: 5381445 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0990. Min Act: -0.1700
Data Index: 262434 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3490. Min Range: -5.3490
Max Act: 5.0677. Min Act: -0.1700
Data Index: 167878 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19