Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.8327. Min Act: -0.1700
Data Index: 5031453 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6765. Min Act: -0.1700
Data Index: 4893457 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6452. Min Act: -0.1700
Data Index: 7485676 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6140. Min Act: -0.1700
Data Index: 1261369 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6140. Min Act: -0.1700
Data Index: 5046375 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4893449 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6140. Min Act: -0.1700
Data Index: 7072820 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6140. Min Act: -0.1700
Data Index: 806817 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.6140. Min Act: -0.1700
Data Index: 5551782 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 5551780 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 1418764 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4650816 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 929467 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5515. Min Act: -0.1700
Data Index: 7524302 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 292069 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5827. Min Act: -0.1700
Data Index: 4231321 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5202. Min Act: -0.1700
Data Index: 1465071 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5515. Min Act: -0.1700
Data Index: 5045338 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5515. Min Act: -0.1700
Data Index: 3772985 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8327. Min Range: -4.8327
Max Act: 4.5515. Min Act: -0.1700
Data Index: 663988 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19