Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5916 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.9668. Min Act: -0.1700
Data Index: 3152926 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.5918. Min Act: -0.1700
Data Index: 408588 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.4043. Min Act: -0.1700
Data Index: 4709599 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.3418. Min Act: -0.1700
Data Index: 394355 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.2793. Min Act: -0.1700
Data Index: 6983227 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.2168. Min Act: -0.1700
Data Index: 6722800 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.1543. Min Act: -0.1700
Data Index: 504280 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.1543. Min Act: -0.1700
Data Index: 7601014 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.1543. Min Act: -0.1700
Data Index: 8496304 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 5116589 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 5577233 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 7714043 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 8241320 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 7452920 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 8268290 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 3653275 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 2939710 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9668. Min Range: -8.9668
Max Act: 7.9668. Min Act: -0.1700
Data Index: 6385536 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 1929146 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9668. Min Range: -8.9668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 5822375 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19