Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 775681 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.5271. Min Act: -0.1700
Data Index: 7708215 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.5271. Min Act: -0.1700
Data Index: 8404087 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.4646. Min Act: -0.1700
Data Index: 7742743 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.3083. Min Act: -0.1700
Data Index: 3298200 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.3083. Min Act: -0.1700
Data Index: 5519931 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.2458. Min Act: -0.1700
Data Index: 5949590 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.2458. Min Act: -0.1700
Data Index: 3090189 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.2146. Min Act: -0.1700
Data Index: 709204 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.2146. Min Act: -0.1700
Data Index: 5977451 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.1521. Min Act: -0.1700
Data Index: 4565296 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.1208. Min Act: -0.1700
Data Index: 5027356 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.1208. Min Act: -0.1700
Data Index: 7066010 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.0583. Min Act: -0.1700
Data Index: 1411262 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.0271. Min Act: -0.1700
Data Index: 6263821 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8083. Min Range: -7.8083
Max Act: 7.0271. Min Act: -0.1700
Data Index: 5604071 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8083. Min Range: -7.8083
Max Act: 6.9646. Min Act: -0.1700
Data Index: 5383163 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8083. Min Range: -7.8083
Max Act: 6.9333. Min Act: -0.1700
Data Index: 1146164 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8083. Min Range: -7.8083
Max Act: 6.9333. Min Act: -0.1700
Data Index: 955336 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8083. Min Range: -7.8083
Max Act: 6.9021. Min Act: -0.1700
Data Index: 5672982 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19