Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.6590. Min Act: -0.1700
Data Index: 7501362 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.6590. Min Act: -0.1700
Data Index: 3267775 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.6277. Min Act: -0.1700
Data Index: 2591253 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.5965. Min Act: -0.1700
Data Index: 910841 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.5652. Min Act: -0.1700
Data Index: 8110404 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.5652. Min Act: -0.1700
Data Index: 4110581 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.5652. Min Act: -0.1700
Data Index: 28917 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4715. Min Act: -0.1700
Data Index: 7499159 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4715. Min Act: -0.1700
Data Index: 5631160 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4402. Min Act: -0.1700
Data Index: 6334582 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4402. Min Act: -0.1700
Data Index: 3217129 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.3777. Min Act: -0.1700
Data Index: 3781741 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4090. Min Act: -0.1700
Data Index: 4733837 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4090. Min Act: -0.1700
Data Index: 6069205 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4090. Min Act: -0.1700
Data Index: 2755814 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4402. Min Act: -0.1700
Data Index: 7428114 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.3777. Min Act: -0.1700
Data Index: 2662165 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4090. Min Act: -0.1700
Data Index: 1035727 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.3777. Min Act: -0.1700
Data Index: 6948352 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6590. Min Range: -6.6590
Max Act: 6.4090. Min Act: -0.1700
Data Index: 849660 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19