Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 487 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7949055 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.7653. Min Act: -0.1700
Data Index: 6196045 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.7028. Min Act: -0.1700
Data Index: 8831289 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.6715. Min Act: -0.1700
Data Index: 6013435 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.6403. Min Act: -0.1700
Data Index: 7511507 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.5778. Min Act: -0.1700
Data Index: 3745524 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.6090. Min Act: -0.1700
Data Index: 3427063 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.6090. Min Act: -0.1700
Data Index: 3417267 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.5778. Min Act: -0.1700
Data Index: 2497619 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.5153. Min Act: -0.1700
Data Index: 1205914 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4215. Min Act: -0.1700
Data Index: 7959865 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4528. Min Act: -0.1700
Data Index: 2242454 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4215. Min Act: -0.1700
Data Index: 222346 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4215. Min Act: -0.1700
Data Index: 3745525 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4215. Min Act: -0.1700
Data Index: 3417268 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.3903. Min Act: -0.1700
Data Index: 2288126 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.3903. Min Act: -0.1700
Data Index: 5674269 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.3903. Min Act: -0.1700
Data Index: 4306545 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.4215. Min Act: -0.1700
Data Index: 2167668 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7965. Min Range: -5.7965
Max Act: 5.3903. Min Act: -0.1700
Data Index: 5414166 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19