Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6105 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2869602 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3344. Min Act: -0.1700
Data Index: 6478760 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3657. Min Act: -0.1700
Data Index: 7249806 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3657. Min Act: -0.1700
Data Index: 6471636 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3344. Min Act: -0.1700
Data Index: 3379772 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3032. Min Act: -0.1700
Data Index: 3878917 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 3251273 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8327870 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 4466837 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 3369673 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3032. Min Act: -0.1700
Data Index: 8318539 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5280462 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.3032. Min Act: -0.1700
Data Index: 4982718 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5932996 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5479890 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2407. Min Act: -0.1700
Data Index: 460557 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1699
Data Index: 2294683 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1700
Data Index: 4275899 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2719. Min Act: -0.1699
Data Index: 2770427 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5219. Min Range: -5.5219
Max Act: 5.2407. Min Act: -0.1700
Data Index: 5038056 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19