Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.9579. Min Act: -0.1700
Data Index: 5714881 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.6766. Min Act: -0.1700
Data Index: 5661196 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.3329. Min Act: -0.1700
Data Index: 7474645 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.2704. Min Act: -0.1700
Data Index: 6061459 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.2079. Min Act: -0.1700
Data Index: 8100315 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.2079. Min Act: -0.1700
Data Index: 1505221 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.1454. Min Act: -0.1700
Data Index: 5414967 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.1141. Min Act: -0.1700
Data Index: 6005612 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.1141. Min Act: -0.1700
Data Index: 2850614 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0829. Min Act: -0.1700
Data Index: 6258679 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0516. Min Act: -0.1700
Data Index: 4955272 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0204. Min Act: -0.1700
Data Index: 1194259 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0516. Min Act: -0.1700
Data Index: 333990 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0204. Min Act: -0.1700
Data Index: 4653450 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9579. Min Range: -7.9579
Max Act: 7.0516. Min Act: -0.1700
Data Index: 455979 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9579. Min Range: -7.9579
Max Act: 6.9891. Min Act: -0.1700
Data Index: 2779830 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9579. Min Range: -7.9579
Max Act: 6.9891. Min Act: -0.1700
Data Index: 2029084 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9579. Min Range: -7.9579
Max Act: 6.9266. Min Act: -0.1700
Data Index: 8286859 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9579. Min Range: -7.9579
Max Act: 6.9266. Min Act: -0.1700
Data Index: 1402646 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9579. Min Range: -7.9579
Max Act: 6.9266. Min Act: -0.1700
Data Index: 5115178 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19