Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 296 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 5353211 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 1947928 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 4255124 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5179. Min Act: -0.1700
Data Index: 8496432 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 6604332 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5179. Min Act: -0.1700
Data Index: 8123976 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4867. Min Act: -0.1700
Data Index: 1797218 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4867. Min Act: -0.1700
Data Index: 4635068 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 449083 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 1677649 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4242. Min Act: -0.1700
Data Index: 715711 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4554. Min Act: -0.1700
Data Index: 2991015 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4242. Min Act: -0.1700
Data Index: 2400182 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4242. Min Act: -0.1700
Data Index: 6686178 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3929. Min Act: -0.1700
Data Index: 897747 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3929. Min Act: -0.1700
Data Index: 1841105 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.4242. Min Act: -0.1700
Data Index: 7058533 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3929. Min Act: -0.1700
Data Index: 3309967 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3929. Min Act: -0.1700
Data Index: 5103790 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.3929. Min Act: -0.1700
Data Index: 372392 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19