Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.6258. Min Act: -0.1700
Data Index: 3559145 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5945. Min Act: -0.1700
Data Index: 7289272 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5788. Min Act: -0.1700
Data Index: 512417 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5475. Min Act: -0.1700
Data Index: 6117446 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5475. Min Act: -0.1700
Data Index: 5412729 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5318. Min Act: -0.1700
Data Index: 6562439 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5162. Min Act: -0.1700
Data Index: 5797827 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5318. Min Act: -0.1700
Data Index: 3396578 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5162. Min Act: -0.1700
Data Index: 1242689 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5005. Min Act: -0.1700
Data Index: 4700031 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4848. Min Act: -0.1700
Data Index: 503458 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5005. Min Act: -0.1700
Data Index: 1879685 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4848. Min Act: -0.1700
Data Index: 3160991 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4848. Min Act: -0.1700
Data Index: 3649137 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4692. Min Act: -0.1700
Data Index: 2052022 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4848. Min Act: -0.1700
Data Index: 8382877 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4848. Min Act: -0.1700
Data Index: 284267 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4692. Min Act: -0.1700
Data Index: 1730106 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5005. Min Act: -0.1700
Data Index: 1422996 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4692. Min Act: -0.1700
Data Index: 4171517 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19