Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0768. Min Range: -5.0768
Max Act: 5.0768. Min Act: -0.1700
Data Index: 8309159 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.9830. Min Act: -0.1700
Data Index: 8727680 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.9518. Min Act: -0.1700
Data Index: 6707659 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.8268. Min Act: -0.1700
Data Index: 3827373 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7955. Min Act: -0.1700
Data Index: 2222045 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7643. Min Act: -0.1700
Data Index: 5311468 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7330. Min Act: -0.1700
Data Index: 6221417 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7330. Min Act: -0.1700
Data Index: 799884 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7330. Min Act: -0.1700
Data Index: 1946559 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 5794355 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 4648454 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7330. Min Act: -0.1700
Data Index: 4818441 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 6177101 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.6705. Min Act: -0.1700
Data Index: 7781152 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.6705. Min Act: -0.1700
Data Index: 1425860 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 6788834 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 4488049 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.7018. Min Act: -0.1700
Data Index: 5759709 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.6705. Min Act: -0.1700
Data Index: 5192388 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0768. Min Range: -5.0768
Max Act: 4.6705. Min Act: -0.1700
Data Index: 5394318 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19