Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0422. Min Range: -8.0422
Max Act: 8.0422. Min Act: -0.1700
Data Index: 4461685 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0422. Min Range: -8.0422
Max Act: 8.0422. Min Act: -0.1700
Data Index: 2745346 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0422. Min Range: -8.0422
Max Act: 8.0422. Min Act: -0.1700
Data Index: 2459050 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.9485. Min Act: -0.1700
Data Index: 6195741 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.8860. Min Act: -0.1700
Data Index: 8571202 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.8860. Min Act: -0.1700
Data Index: 31298 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.8860. Min Act: -0.1700
Data Index: 5228950 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.8547. Min Act: -0.1700
Data Index: 6004928 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.8547. Min Act: -0.1700
Data Index: 4730709 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.7922. Min Act: -0.1700
Data Index: 5076765 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.7297. Min Act: -0.1700
Data Index: 2178925 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.7610. Min Act: -0.1700
Data Index: 1729172 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.7610. Min Act: -0.1700
Data Index: 6294164 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.7297. Min Act: -0.1700
Data Index: 3127669 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6672. Min Act: -0.1700
Data Index: 5052470 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6047. Min Act: -0.1700
Data Index: 4233591 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6360. Min Act: -0.1700
Data Index: 1090264 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6360. Min Act: -0.1700
Data Index: 6097900 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6047. Min Act: -0.1700
Data Index: 310556 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0422. Min Range: -8.0422
Max Act: 7.6047. Min Act: -0.1700
Data Index: 298686 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19