Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5326 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.2476. Min Act: -0.1700
Data Index: 3012609 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.2163. Min Act: -0.1700
Data Index: 4547634 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.1851. Min Act: -0.1700
Data Index: 7176284 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.1538. Min Act: -0.1700
Data Index: 676032 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.1226. Min Act: -0.1700
Data Index: 7121308 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0601. Min Act: -0.1700
Data Index: 3785222 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0913. Min Act: -0.1700
Data Index: 3929507 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0601. Min Act: -0.1700
Data Index: 3492689 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0601. Min Act: -0.1700
Data Index: 797833 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 3745613 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5542641 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2476. Min Range: -5.2476
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5376165 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3082897 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 845612 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9976. Min Act: -0.1700
Data Index: 796955 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9663. Min Act: -0.1700
Data Index: 3074223 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9663. Min Act: -0.1700
Data Index: 8596513 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9663. Min Act: -0.1700
Data Index: 1928563 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9663. Min Act: -0.1700
Data Index: 7633991 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2476. Min Range: -5.2476
Max Act: 4.9038. Min Act: -0.1700
Data Index: 2197048 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19