Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.7070. Min Act: -0.1700
Data Index: 3238902 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.7070. Min Act: -0.1700
Data Index: 7132229 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.5820. Min Act: -0.1700
Data Index: 6318411 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.5195. Min Act: -0.1700
Data Index: 4144749 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4882. Min Act: -0.1700
Data Index: 67617 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1813070 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.4257. Min Act: -0.1700
Data Index: 8698270 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 4807881 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3945. Min Act: -0.1700
Data Index: 2954844 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3632. Min Act: -0.1700
Data Index: 6455696 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 5915009 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 4139146 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3007. Min Act: -0.1700
Data Index: 1926412 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 3238903 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 3238906 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.3320. Min Act: -0.1700
Data Index: 3200785 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.2382. Min Act: -0.1700
Data Index: 4807884 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.2382. Min Act: -0.1700
Data Index: 2075438 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.2695. Min Act: -0.1700
Data Index: 1515717 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7070. Min Range: -4.7070
Max Act: 4.1444. Min Act: -0.1700
Data Index: 3040839 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19