Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3014 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.8203. Min Act: -0.1700
Data Index: 554783 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.7577. Min Act: -0.1700
Data Index: 6936509 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6952. Min Act: -0.1700
Data Index: 8086482 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6639. Min Act: -0.1700
Data Index: 8013123 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6639. Min Act: -0.1700
Data Index: 5407509 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6013. Min Act: -0.1700
Data Index: 1299230 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6013. Min Act: -0.1700
Data Index: 8013111 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.6013. Min Act: -0.1700
Data Index: 2718438 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.5700. Min Act: -0.1700
Data Index: 104208 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.5387. Min Act: -0.1700
Data Index: 6016986 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.5387. Min Act: -0.1700
Data Index: 7742045 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4760. Min Act: -0.1700
Data Index: 2256144 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4760. Min Act: -0.1700
Data Index: 1775530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4447. Min Act: -0.1700
Data Index: 6928804 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4447. Min Act: -0.1700
Data Index: 4266562 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4447. Min Act: -0.1700
Data Index: 1458910 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4447. Min Act: -0.1700
Data Index: 703790 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4133. Min Act: -0.1700
Data Index: 3858491 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.4133. Min Act: -0.1700
Data Index: 1699869 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8203. Min Range: -3.8203
Max Act: 3.3820. Min Act: -0.1700
Data Index: 3597237 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19