Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.5455. Min Act: -0.1700
Data Index: 1361839 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4808. Min Act: -0.1700
Data Index: 1120511 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4320. Min Act: -0.1700
Data Index: 2924431 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4320. Min Act: -0.1700
Data Index: 6069963 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4320. Min Act: -0.1700
Data Index: 6135135 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4320. Min Act: -0.1700
Data Index: 6352162 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4157. Min Act: -0.1700
Data Index: 6478820 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4157. Min Act: -0.1700
Data Index: 6532237 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3994. Min Act: -0.1700
Data Index: 7488856 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4157. Min Act: -0.1700
Data Index: 5010990 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3994. Min Act: -0.1700
Data Index: 5223655 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3667. Min Act: -0.1700
Data Index: 5589257 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3831. Min Act: -0.1700
Data Index: 8020941 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3831. Min Act: -0.1700
Data Index: 2755610 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3831. Min Act: -0.1700
Data Index: 4132995 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3667. Min Act: -0.1700
Data Index: 4131715 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3994. Min Act: -0.1700
Data Index: 1929747 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.4157. Min Act: -0.1700
Data Index: 239478 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3667. Min Act: -0.1700
Data Index: 612312 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5455. Min Range: -2.5455
Max Act: 2.3667. Min Act: -0.1700
Data Index: 2755612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19