Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2843 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.7069. Min Act: -0.1700
Data Index: 6693708 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.6132. Min Act: -0.1700
Data Index: 436274 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.5819. Min Act: -0.1700
Data Index: 6650146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.5194. Min Act: -0.1700
Data Index: 7234329 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4569. Min Act: -0.1700
Data Index: 1209387 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4569. Min Act: -0.1700
Data Index: 376773 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4569. Min Act: -0.1700
Data Index: 5273662 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4569. Min Act: -0.1700
Data Index: 4903264 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4569. Min Act: -0.1700
Data Index: 4809561 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4257. Min Act: -0.1700
Data Index: 1115818 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4257. Min Act: -0.1700
Data Index: 258386 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.4257. Min Act: -0.1700
Data Index: 4404502 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3944. Min Act: -0.1700
Data Index: 1356288 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3944. Min Act: -0.1700
Data Index: 6399981 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3944. Min Act: -0.1700
Data Index: 2017332 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3632. Min Act: -0.1700
Data Index: 8413024 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3944. Min Act: -0.1700
Data Index: 4965135 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3944. Min Act: -0.1700
Data Index: 7778821 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3632. Min Act: -0.1700
Data Index: 2187962 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7069. Min Range: -4.7069
Max Act: 4.3632. Min Act: -0.1700
Data Index: 2526419 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19