Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1086. Min Range: -3.1086
Max Act: 3.1086. Min Act: -0.1700
Data Index: 5403407 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1086. Min Range: -3.1086
Max Act: 3.0455. Min Act: -0.1700
Data Index: 8671592 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1086. Min Range: -3.1086
Max Act: 3.0140. Min Act: -0.1700
Data Index: 5121102 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9824. Min Act: -0.1700
Data Index: 4789460 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9665. Min Act: -0.1700
Data Index: 6729127 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9349. Min Act: -0.1700
Data Index: 1094890 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9507. Min Act: -0.1700
Data Index: 4871097 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9507. Min Act: -0.1700
Data Index: 4149903 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9507. Min Act: -0.1700
Data Index: 1784222 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 108844 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9349. Min Act: -0.1700
Data Index: 7500247 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9349. Min Act: -0.1700
Data Index: 5305030 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 4596836 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 93160 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 6978116 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 7029612 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 1970621 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.9190. Min Act: -0.1700
Data Index: 6729135 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.8873. Min Act: -0.1700
Data Index: 6454957 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1086. Min Range: -3.1086
Max Act: 2.8873. Min Act: -0.1700
Data Index: 6729117 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19