Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0882. Min Range: -7.0882
Max Act: 7.0882. Min Act: -0.1700
Data Index: 2428094 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0882. Min Range: -7.0882
Max Act: 7.0257. Min Act: -0.1700
Data Index: 7811673 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0882. Min Range: -7.0882
Max Act: 7.0570. Min Act: -0.1700
Data Index: 1416562 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.9632. Min Act: -0.1700
Data Index: 3728232 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.9320. Min Act: -0.1700
Data Index: 6677461 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.9320. Min Act: -0.1700
Data Index: 8555919 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.9007. Min Act: -0.1700
Data Index: 4035501 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.8382. Min Act: -0.1700
Data Index: 1331701 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.8382. Min Act: -0.1700
Data Index: 3175730 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.8382. Min Act: -0.1700
Data Index: 5787500 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.8382. Min Act: -0.1700
Data Index: 3030045 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.8070. Min Act: -0.1700
Data Index: 2593085 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.7757. Min Act: -0.1700
Data Index: 6603559 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.7757. Min Act: -0.1700
Data Index: 7336337 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.7132. Min Act: -0.1700
Data Index: 5047363 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.6820. Min Act: -0.1700
Data Index: 2291020 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.7132. Min Act: -0.1700
Data Index: 2634175 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.6820. Min Act: -0.1700
Data Index: 6700811 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.6820. Min Act: -0.1700
Data Index: 5818378 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0882. Min Range: -7.0882
Max Act: 6.6507. Min Act: -0.1700
Data Index: 6121492 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19