Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.6393. Min Act: -0.1700
Data Index: 2081098 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.4206. Min Act: -0.1700
Data Index: 2425947 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.2018. Min Act: -0.1700
Data Index: 656414 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.1706. Min Act: -0.1700
Data Index: 7803620 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.2018. Min Act: -0.1700
Data Index: 2723575 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.1081. Min Act: -0.1700
Data Index: 4607928 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6278132 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0768. Min Act: -0.1700
Data Index: 7770666 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5439606 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5948647 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5671081 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0143. Min Act: -0.1700
Data Index: 2749476 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7783458 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0143. Min Act: -0.1700
Data Index: 3874828 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6393. Min Range: -6.6393
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7301803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6393. Min Range: -6.6393
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5012381 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6393. Min Range: -6.6393
Max Act: 5.9518. Min Act: -0.1700
Data Index: 5369075 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6393. Min Range: -6.6393
Max Act: 5.9831. Min Act: -0.1700
Data Index: 6471678 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6393. Min Range: -6.6393
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2302687 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6393. Min Range: -6.6393
Max Act: 5.9831. Min Act: -0.1700
Data Index: 5429582 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19