Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0103. Min Range: -6.0103
Max Act: 6.0103. Min Act: -0.1700
Data Index: 1593779 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.9166. Min Act: -0.1700
Data Index: 2416186 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.8853. Min Act: -0.1700
Data Index: 548487 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.8541. Min Act: -0.1700
Data Index: 5552622 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.7916. Min Act: -0.1700
Data Index: 8239761 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.7291. Min Act: -0.1700
Data Index: 5260559 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.7603. Min Act: -0.1700
Data Index: 3203085 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.6666. Min Act: -0.1700
Data Index: 2596000 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.5416. Min Act: -0.1700
Data Index: 7892913 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.5103. Min Act: -0.1700
Data Index: 1918230 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.5103. Min Act: -0.1700
Data Index: 877403 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4478. Min Act: -0.1700
Data Index: 5128162 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4478. Min Act: -0.1700
Data Index: 888084 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4478. Min Act: -0.1700
Data Index: 4941906 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4166. Min Act: -0.1700
Data Index: 5111000 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4166. Min Act: -0.1700
Data Index: 8342684 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.4166. Min Act: -0.1700
Data Index: 1589962 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.3853. Min Act: -0.1700
Data Index: 738707 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.3853. Min Act: -0.1700
Data Index: 2407674 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0103. Min Range: -6.0103
Max Act: 5.3541. Min Act: -0.1700
Data Index: 2308492 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19