Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5663 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.9299. Min Act: -0.1700
Data Index: 6023956 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8987. Min Act: -0.1700
Data Index: 4807114 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8987. Min Act: -0.1700
Data Index: 5122166 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8987. Min Act: -0.1700
Data Index: 1384083 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 4926253 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8987. Min Act: -0.1700
Data Index: 1233145 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8674. Min Act: -0.1700
Data Index: 1867047 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8674. Min Act: -0.1700
Data Index: 7624255 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1517753 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 3966595 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 3580501 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 4180362 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 1313528 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8674. Min Act: -0.1700
Data Index: 3792850 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 6215509 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 6530856 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8362. Min Act: -0.1700
Data Index: 7374498 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8049. Min Act: -0.1700
Data Index: 5942917 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8049. Min Act: -0.1700
Data Index: 3312674 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9299. Min Range: -4.9299
Max Act: 4.8049. Min Act: -0.1700
Data Index: 2698076 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19