Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.6407. Min Act: -0.1700
Data Index: 5830969 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.5782. Min Act: -0.1700
Data Index: 6514774 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.4532. Min Act: -0.1700
Data Index: 6013903 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.2032. Min Act: -0.1700
Data Index: 6356453 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.3282. Min Act: -0.1700
Data Index: 1644422 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.2032. Min Act: -0.1700
Data Index: 2848294 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.2032. Min Act: -0.1700
Data Index: 4938508 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.2032. Min Act: -0.1700
Data Index: 773465 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.2032. Min Act: -0.1700
Data Index: 4782413 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.1407. Min Act: -0.1700
Data Index: 5606200 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.1407. Min Act: -0.1700
Data Index: 1274969 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0782. Min Act: -0.1700
Data Index: 8645050 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0782. Min Act: -0.1700
Data Index: 4599112 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0782. Min Act: -0.1700
Data Index: 246445 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0782. Min Act: -0.1700
Data Index: 4284360 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0782. Min Act: -0.1700
Data Index: 1325053 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0157. Min Act: -0.1700
Data Index: 234158 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0157. Min Act: -0.1700
Data Index: 739845 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6407. Min Range: -8.6407
Max Act: 8.0157. Min Act: -0.1700
Data Index: 4670112 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6407. Min Range: -8.6407
Max Act: 7.9532. Min Act: -0.1700
Data Index: 3536848 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19