Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2050 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.4810. Min Act: -0.1700
Data Index: 7278902 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.4498. Min Act: -0.1700
Data Index: 7321001 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.3248. Min Act: -0.1700
Data Index: 1572277 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1685. Min Act: -0.1700
Data Index: 359974 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1060. Min Act: -0.1700
Data Index: 2463189 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1060. Min Act: -0.1700
Data Index: 86999 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.1060. Min Act: -0.1700
Data Index: 8754277 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.0123. Min Act: -0.1700
Data Index: 8363416 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4810. Min Range: -7.4810
Max Act: 7.0435. Min Act: -0.1700
Data Index: 1843573 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9810. Min Act: -0.1700
Data Index: 5151175 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9185. Min Act: -0.1700
Data Index: 3505729 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.9185. Min Act: -0.1700
Data Index: 4424825 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8873. Min Act: -0.1700
Data Index: 5652791 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8873. Min Act: -0.1700
Data Index: 6857858 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.8248. Min Act: -0.1700
Data Index: 4063279 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7935. Min Act: -0.1700
Data Index: 461180 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7623. Min Act: -0.1700
Data Index: 2359575 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7310. Min Act: -0.1700
Data Index: 6799524 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7623. Min Act: -0.1700
Data Index: 1681119 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4810. Min Range: -7.4810
Max Act: 6.7310. Min Act: -0.1700
Data Index: 1560598 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19