Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5340 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.5191. Min Act: -0.1700
Data Index: 4406980 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.3941. Min Act: -0.1700
Data Index: 7701281 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.3628. Min Act: -0.1700
Data Index: 47516 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.3316. Min Act: -0.1700
Data Index: 7799084 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.3003. Min Act: -0.1700
Data Index: 5657233 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.3003. Min Act: -0.1700
Data Index: 1422227 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2691. Min Act: -0.1700
Data Index: 7597971 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2691. Min Act: -0.1700
Data Index: 6684293 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2691. Min Act: -0.1700
Data Index: 3291929 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2378. Min Act: -0.1700
Data Index: 2505271 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2691. Min Act: -0.1700
Data Index: 4098803 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2378. Min Act: -0.1700
Data Index: 8524969 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2066. Min Act: -0.1700
Data Index: 1969356 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2066. Min Act: -0.1700
Data Index: 6976398 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.2066. Min Act: -0.1700
Data Index: 2262403 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.1753. Min Act: -0.1700
Data Index: 800120 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.1753. Min Act: -0.1700
Data Index: 6294425 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.1753. Min Act: -0.1700
Data Index: 206916 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.1753. Min Act: -0.1700
Data Index: 7916219 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5191. Min Range: -4.5191
Max Act: 4.1753. Min Act: -0.1700
Data Index: 2232538 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19