Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.8720. Min Act: -0.1700
Data Index: 8758401 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.7470. Min Act: -0.1700
Data Index: 701704 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.7158. Min Act: -0.1700
Data Index: 2185453 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.7158. Min Act: -0.1700
Data Index: 2024978 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.7158. Min Act: -0.1700
Data Index: 8151985 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.7470. Min Act: -0.1700
Data Index: 7763095 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 3664058 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 1988558 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 8283344 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6845. Min Act: -0.1700
Data Index: 7967180 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6845. Min Act: -0.1700
Data Index: 3926016 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 546451 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 5643704 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6845. Min Act: -0.1700
Data Index: 4621280 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6220. Min Act: -0.1700
Data Index: 6465576 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6533. Min Act: -0.1700
Data Index: 1898026 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6220. Min Act: -0.1700
Data Index: 3506602 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5845710 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.6220. Min Act: -0.1700
Data Index: 1250595 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8720. Min Range: -4.8720
Max Act: 4.5595. Min Act: -0.1700
Data Index: 3648424 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19