Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.4622. Min Act: -0.1700
Data Index: 8629165 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.3372. Min Act: -0.1700
Data Index: 6682369 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.2747. Min Act: -0.1700
Data Index: 7991734 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.2435. Min Act: -0.1700
Data Index: 5246533 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4622. Min Range: -7.4622
Max Act: 7.1185. Min Act: -0.1700
Data Index: 6200296 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9935. Min Act: -0.1700
Data Index: 4807926 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 3687371 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 5420277 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 4064991 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 3707255 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8997. Min Act: -0.1700
Data Index: 744434 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8685. Min Act: -0.1700
Data Index: 882452 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8685. Min Act: -0.1700
Data Index: 1060811 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8685. Min Act: -0.1700
Data Index: 2797938 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8685. Min Act: -0.1700
Data Index: 7739293 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8372. Min Act: -0.1700
Data Index: 2951274 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8372. Min Act: -0.1700
Data Index: 8626889 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8372. Min Act: -0.1700
Data Index: 3209278 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8060. Min Act: -0.1700
Data Index: 2875132 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4622. Min Range: -7.4622
Max Act: 6.8060. Min Act: -0.1700
Data Index: 6994447 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19