Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4960 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8579. Min Range: -5.8579
Max Act: 5.8579. Min Act: -0.1700
Data Index: 6944669 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.9829. Min Act: -0.1700
Data Index: 2969525 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.9516. Min Act: -0.1700
Data Index: 8637828 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.9204. Min Act: -0.1700
Data Index: 8285110 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.8891. Min Act: -0.1700
Data Index: 2203484 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.8579. Min Act: -0.1700
Data Index: 4807924 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.8266. Min Act: -0.1700
Data Index: 6495714 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.7954. Min Act: -0.1700
Data Index: 7683825 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.7954. Min Act: -0.1700
Data Index: 5877028 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6704. Min Act: -0.1700
Data Index: 746515 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 3307936 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6391. Min Act: -0.1700
Data Index: 1045236 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6391. Min Act: -0.1700
Data Index: 4181870 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.5766. Min Act: -0.1700
Data Index: 8777463 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 3447301 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 626938 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 1525713 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 7517990 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.6079. Min Act: -0.1700
Data Index: 642376 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8579. Min Range: -5.8579
Max Act: 4.5766. Min Act: -0.1700
Data Index: 750105 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19