Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.5021. Min Act: -0.1700
Data Index: 3544943 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.2521. Min Act: -0.1700
Data Index: 7411829 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.1896. Min Act: -0.1700
Data Index: 6684189 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.1896. Min Act: -0.1700
Data Index: 2833699 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.1271. Min Act: -0.1700
Data Index: 5022232 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.1271. Min Act: -0.1700
Data Index: 1970526 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.1271. Min Act: -0.1700
Data Index: 4680145 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0959. Min Act: -0.1700
Data Index: 5147729 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 19095 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 2051119 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 3271364 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0646. Min Act: -0.1700
Data Index: 6829735 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5021. Min Range: -7.5021
Max Act: 7.0334. Min Act: -0.1700
Data Index: 1371577 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9396. Min Act: -0.1700
Data Index: 2062091 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9396. Min Act: -0.1700
Data Index: 6317959 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9709. Min Act: -0.1700
Data Index: 6911187 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9396. Min Act: -0.1700
Data Index: 7715952 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9396. Min Act: -0.1700
Data Index: 5789109 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9396. Min Act: -0.1700
Data Index: 6517037 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5021. Min Range: -7.5021
Max Act: 6.9084. Min Act: -0.1700
Data Index: 6476557 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19