Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6132. Min Range: -5.6132
Max Act: 5.6132. Min Act: -0.1700
Data Index: 4833081 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6132. Min Range: -5.6132
Max Act: 5.1757. Min Act: -0.1700
Data Index: 7553694 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 2767880 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 6457532 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 207113 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 4514923 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 5512307 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9882. Min Act: -0.1700
Data Index: 8119586 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9570. Min Act: -0.1700
Data Index: 2011790 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9570. Min Act: -0.1700
Data Index: 2370850 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9570. Min Act: -0.1700
Data Index: 2155634 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9257. Min Act: -0.1700
Data Index: 6654518 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9257. Min Act: -0.1700
Data Index: 2016393 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.9257. Min Act: -0.1700
Data Index: 567963 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4823330 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8945. Min Act: -0.1700
Data Index: 4040939 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 5936034 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 194447 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 2351037 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6132. Min Range: -5.6132
Max Act: 4.8632. Min Act: -0.1700
Data Index: 3948335 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19