Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.9240. Min Act: -0.1700
Data Index: 5680578 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5803. Min Act: -0.1700
Data Index: 7301325 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.6115. Min Act: -0.1700
Data Index: 6646963 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5490. Min Act: -0.1700
Data Index: 777172 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5490. Min Act: -0.1700
Data Index: 2230952 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5178. Min Act: -0.1700
Data Index: 2217622 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5178. Min Act: -0.1700
Data Index: 1888431 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5178. Min Act: -0.1700
Data Index: 7321613 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.5178. Min Act: -0.1700
Data Index: 1853355 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.4865. Min Act: -0.1700
Data Index: 60881 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.4865. Min Act: -0.1700
Data Index: 7336548 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 6579092 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 3154442 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 4678809 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3615. Min Act: -0.1700
Data Index: 66995 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3928. Min Act: -0.1700
Data Index: 3373902 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3928. Min Act: -0.1700
Data Index: 8620476 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3615. Min Act: -0.1700
Data Index: 7304337 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3615. Min Act: -0.1700
Data Index: 2367218 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9240. Min Range: -6.9240
Max Act: 6.3615. Min Act: -0.1700
Data Index: 8053411 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19