Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.5544. Min Act: -0.1700
Data Index: 3941658 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.3669. Min Act: -0.1700
Data Index: 2642744 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.3669. Min Act: -0.1700
Data Index: 3454503 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.1169. Min Act: -0.1700
Data Index: 3825274 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.1169. Min Act: -0.1700
Data Index: 1921569 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.0544. Min Act: -0.1700
Data Index: 8049926 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.0544. Min Act: -0.1700
Data Index: 2102433 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.0544. Min Act: -0.1700
Data Index: 7766284 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9919. Min Act: -0.1700
Data Index: 1569074 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9919. Min Act: -0.1700
Data Index: 8229276 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9919. Min Act: -0.1700
Data Index: 7938143 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5544. Min Range: -8.5544
Max Act: 8.0544. Min Act: -0.1700
Data Index: 3202739 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9919. Min Act: -0.1700
Data Index: 5089167 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 2642745 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 4399983 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 7678194 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 277033 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 3260561 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 7013936 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5544. Min Range: -8.5544
Max Act: 7.9294. Min Act: -0.1700
Data Index: 885980 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19