Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4287 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.8672. Min Act: -0.1503
Data Index: 6681281 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.8360. Min Act: -0.1700
Data Index: 8139456 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.8360. Min Act: -0.1503
Data Index: 7096884 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7109778 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3971346 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8294056 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.6172. Min Act: -0.1503
Data Index: 7980777 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.5860. Min Act: -0.1700
Data Index: 1377851 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.5547. Min Act: -0.1503
Data Index: 680092 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.5547. Min Act: -0.1699
Data Index: 987627 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4922. Min Act: -0.1547
Data Index: 680090 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.5235. Min Act: -0.1700
Data Index: 8595660 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.5547. Min Act: -0.1547
Data Index: 2949108 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4922. Min Act: -0.1697
Data Index: 863317 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1503
Data Index: 7980774 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1547
Data Index: 6681280 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1700
Data Index: 6556991 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1503
Data Index: 2949111 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1700
Data Index: 2433156 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8672. Min Range: -5.8672
Max Act: 5.4610. Min Act: -0.1700
Data Index: 2596761 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19