Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.8201. Min Act: -0.1700
Data Index: 563761 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.6326. Min Act: -0.1700
Data Index: 5716512 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.2576. Min Act: -0.1700
Data Index: 4863681 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.2576. Min Act: -0.1700
Data Index: 5012822 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.1951. Min Act: -0.1700
Data Index: 3627259 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.0701. Min Act: -0.1700
Data Index: 1545797 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.0701. Min Act: -0.1700
Data Index: 2833442 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8201. Min Range: -10.8201
Max Act: 10.0076. Min Act: -0.1700
Data Index: 4642432 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.9451. Min Act: -0.1700
Data Index: 8293226 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 6179555 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8201. Min Act: -0.1700
Data Index: 2148232 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 2891777 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1699
Data Index: 1598478 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 1671085 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8201. Min Act: -0.1700
Data Index: 6869000 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 2963088 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 6143981 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8201. Min Act: -0.1700
Data Index: 7698123 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.8826. Min Act: -0.1700
Data Index: 6179554 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8201. Min Range: -10.8201
Max Act: 9.7576. Min Act: -0.1700
Data Index: 5694545 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19