Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4194. Min Range: -4.4194
Max Act: 4.4194. Min Act: -0.1700
Data Index: 2729207 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4194. Min Range: -4.4194
Max Act: 4.2319. Min Act: -0.1700
Data Index: 4256285 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4194. Min Range: -4.4194
Max Act: 4.2006. Min Act: -0.1700
Data Index: 8083822 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.9818. Min Act: -0.1700
Data Index: 2272146 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.9193. Min Act: -0.1700
Data Index: 3960066 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.9193. Min Act: -0.1700
Data Index: 2936020 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.9193. Min Act: -0.1700
Data Index: 4383678 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.9193. Min Act: -0.1700
Data Index: 4928769 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8880. Min Act: -0.1700
Data Index: 948535 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8568. Min Act: -0.1700
Data Index: 4508345 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8411. Min Act: -0.1700
Data Index: 7670735 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8098. Min Act: -0.1700
Data Index: 5994150 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8255. Min Act: -0.1700
Data Index: 705588 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.8255. Min Act: -0.1700
Data Index: 3965534 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7942. Min Act: -0.1700
Data Index: 196016 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7942. Min Act: -0.1700
Data Index: 5554366 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7942. Min Act: -0.1700
Data Index: 2410949 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7942. Min Act: -0.1700
Data Index: 4954133 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7786. Min Act: -0.1700
Data Index: 5689761 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4194. Min Range: -4.4194
Max Act: 3.7786. Min Act: -0.1700
Data Index: 8085646 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19