Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 224 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.4433. Min Act: -0.1700
Data Index: 6938614 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.4120. Min Act: -0.1700
Data Index: 4761077 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3806. Min Act: -0.1700
Data Index: 4062490 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3650. Min Act: -0.1700
Data Index: 8514670 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3806. Min Act: -0.1700
Data Index: 3304640 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3336. Min Act: -0.1700
Data Index: 1189485 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3179. Min Act: -0.1700
Data Index: 7733459 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3022. Min Act: -0.1700
Data Index: 7141656 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.3022. Min Act: -0.1700
Data Index: 5528773 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2394. Min Act: -0.1700
Data Index: 7109873 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2551. Min Act: -0.1700
Data Index: 5100708 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2708. Min Act: -0.1700
Data Index: 5955197 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2394. Min Act: -0.1700
Data Index: 656960 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2394. Min Act: -0.1700
Data Index: 3737404 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2394. Min Act: -0.1700
Data Index: 8252054 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2236. Min Act: -0.1700
Data Index: 2415248 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2079. Min Act: -0.1700
Data Index: 7138947 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2079. Min Act: -0.1700
Data Index: 8167077 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.1922. Min Act: -0.1700
Data Index: 3850109 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4433. Min Range: -3.4433
Max Act: 3.2236. Min Act: -0.1700
Data Index: 7634415 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19