Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0899. Min Range: -9.0899
Max Act: 9.0899. Min Act: -0.1700
Data Index: 4598602 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.9649. Min Act: -0.1700
Data Index: 8647065 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.7149. Min Act: -0.1700
Data Index: 3745534 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.6524. Min Act: -0.1700
Data Index: 4200357 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.7149. Min Act: -0.1700
Data Index: 8445903 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.5899. Min Act: -0.1700
Data Index: 6134362 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.5274. Min Act: -0.1700
Data Index: 887950 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.5274. Min Act: -0.1700
Data Index: 6809284 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.5274. Min Act: -0.1700
Data Index: 7624720 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4649. Min Act: -0.1700
Data Index: 4924806 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4649. Min Act: -0.1700
Data Index: 2283512 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4649. Min Act: -0.1700
Data Index: 5750248 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4649. Min Act: -0.1700
Data Index: 8351095 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4024. Min Act: -0.1700
Data Index: 6167031 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4024. Min Act: -0.1700
Data Index: 7911324 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.3399. Min Act: -0.1700
Data Index: 2285562 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4024. Min Act: -0.1700
Data Index: 4324456 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.4024. Min Act: -0.1700
Data Index: 1935992 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.3399. Min Act: -0.1700
Data Index: 992763 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0899. Min Range: -9.0899
Max Act: 8.3399. Min Act: -0.1700
Data Index: 837476 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19