Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3354 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1137. Min Range: -7.1137
Max Act: 7.1137. Min Act: -0.1700
Data Index: 8776160 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.8325. Min Act: -0.1700
Data Index: 4132343 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.7700. Min Act: -0.1700
Data Index: 7647504 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.6762. Min Act: -0.1700
Data Index: 2637984 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.6137. Min Act: -0.1700
Data Index: 1525138 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.6137. Min Act: -0.1700
Data Index: 6407508 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.5512. Min Act: -0.1700
Data Index: 7448974 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.5512. Min Act: -0.1700
Data Index: 4807855 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.4887. Min Act: -0.1700
Data Index: 1820806 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.4575. Min Act: -0.1700
Data Index: 5193763 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.4262. Min Act: -0.1700
Data Index: 349838 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.3950. Min Act: -0.1700
Data Index: 197581 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.3950. Min Act: -0.1700
Data Index: 8648426 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.3637. Min Act: -0.1700
Data Index: 103957 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.2700. Min Act: -0.1700
Data Index: 8221833 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.2700. Min Act: -0.1700
Data Index: 3413942 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.2075. Min Act: -0.1700
Data Index: 184581 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.1762. Min Act: -0.1700
Data Index: 1697339 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.1762. Min Act: -0.1700
Data Index: 4067722 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1137. Min Range: -7.1137
Max Act: 6.1762. Min Act: -0.1700
Data Index: 6684693 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19