Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2506 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.8061. Min Act: -0.1700
Data Index: 2277764 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.6184. Min Act: -0.1700
Data Index: 2950496 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.6497. Min Act: -0.1700
Data Index: 4018741 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.6184. Min Act: -0.1700
Data Index: 2410906 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.5871. Min Act: -0.1700
Data Index: 3159372 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.5871. Min Act: -0.1700
Data Index: 8066938 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.5245. Min Act: -0.1700
Data Index: 5222403 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.5245. Min Act: -0.1700
Data Index: 6829600 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.5245. Min Act: -0.1700
Data Index: 5367348 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4932. Min Act: -0.1700
Data Index: 6526486 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4932. Min Act: -0.1700
Data Index: 2002574 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4775. Min Act: -0.1700
Data Index: 3023545 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4932. Min Act: -0.1700
Data Index: 2345539 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4932. Min Act: -0.1700
Data Index: 3392270 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4775. Min Act: -0.1700
Data Index: 4141534 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4775. Min Act: -0.1700
Data Index: 5096095 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4618. Min Act: -0.1700
Data Index: 3183142 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4618. Min Act: -0.1700
Data Index: 3504565 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4462. Min Act: -0.1700
Data Index: 183101 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8061. Min Range: -3.8061
Max Act: 3.4462. Min Act: -0.1700
Data Index: 8833 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19