Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.6165. Min Act: -0.1700
Data Index: 4942948 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.5853. Min Act: -0.1700
Data Index: 6353783 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.5540. Min Act: -0.1700
Data Index: 6705750 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.4290. Min Act: -0.1700
Data Index: 226561 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3978. Min Act: -0.1700
Data Index: 5681435 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.4290. Min Act: -0.1700
Data Index: 175089 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3978. Min Act: -0.1700
Data Index: 7775536 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3665. Min Act: -0.1700
Data Index: 4868886 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3665. Min Act: -0.1700
Data Index: 489235 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3353. Min Act: -0.1700
Data Index: 4506621 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3665. Min Act: -0.1700
Data Index: 622896 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3665. Min Act: -0.1700
Data Index: 1854062 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3353. Min Act: -0.1700
Data Index: 2239317 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3353. Min Act: -0.1700
Data Index: 4942946 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3665. Min Act: -0.1700
Data Index: 7941324 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.4290. Min Act: -0.1700
Data Index: 1732059 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.2728. Min Act: -0.1700
Data Index: 1732061 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.2728. Min Act: -0.1700
Data Index: 4041645 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3353. Min Act: -0.1700
Data Index: 355261 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6165. Min Range: -4.6165
Max Act: 4.3353. Min Act: -0.1700
Data Index: 6891430 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19