Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4175 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.7248. Min Act: -0.1700
Data Index: 2152612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6728. Min Act: -0.1700
Data Index: 3489100 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6554. Min Act: -0.1700
Data Index: 6616938 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6554. Min Act: -0.1695
Data Index: 774869 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6554. Min Act: -0.1700
Data Index: 8780934 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6380. Min Act: -0.1700
Data Index: 1310007 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6554. Min Act: -0.1699
Data Index: 5978003 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6205. Min Act: -0.1700
Data Index: 1593184 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6031. Min Act: -0.1700
Data Index: 1315716 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6031. Min Act: -0.1700
Data Index: 6046636 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6205. Min Act: -0.1700
Data Index: 4480638 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.6031. Min Act: -0.1700
Data Index: 7357104 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5944. Min Act: -0.1695
Data Index: 6464851 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5856. Min Act: -0.1699
Data Index: 5919968 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5856. Min Act: -0.1699
Data Index: 2153810 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5769. Min Act: -0.1700
Data Index: 476383 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5856. Min Act: -0.1700
Data Index: 8267575 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5856. Min Act: -0.1700
Data Index: 5199858 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5856. Min Act: -0.1700
Data Index: 3954517 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7248. Min Range: -1.7248
Max Act: 1.5769. Min Act: -0.1700
Data Index: 1239368 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19