Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4796 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.5054. Min Act: -0.1700
Data Index: 6309912 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.4429. Min Act: -0.1700
Data Index: 3014203 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.4429. Min Act: -0.1700
Data Index: 3014199 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.4117. Min Act: -0.1700
Data Index: 8709497 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.3804. Min Act: -0.1700
Data Index: 3014191 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.3179. Min Act: -0.1700
Data Index: 3014187 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.2867. Min Act: -0.1700
Data Index: 4860233 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.1929. Min Act: -0.1700
Data Index: 5366373 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.1617. Min Act: -0.1700
Data Index: 3014195 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.1304. Min Act: -0.1700
Data Index: 5128365 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0992. Min Act: -0.1700
Data Index: 7550367 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0992. Min Act: -0.1700
Data Index: 1431244 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0679. Min Act: -0.1700
Data Index: 33992 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0679. Min Act: -0.1700
Data Index: 3503958 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0367. Min Act: -0.1700
Data Index: 2982672 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0679. Min Act: -0.1700
Data Index: 4565293 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0367. Min Act: -0.1700
Data Index: 8121811 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5054. Min Range: -7.5054
Max Act: 7.0054. Min Act: -0.1700
Data Index: 6131577 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5054. Min Range: -7.5054
Max Act: 6.9742. Min Act: -0.1700
Data Index: 6170562 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5054. Min Range: -7.5054
Max Act: 6.9429. Min Act: -0.1700
Data Index: 1871540 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19