Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1217 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.7560. Min Act: -0.1700
Data Index: 6224858 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.7248. Min Act: -0.1700
Data Index: 4556457 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.6935. Min Act: -0.1700
Data Index: 486005 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.7248. Min Act: -0.1700
Data Index: 5801916 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.6310. Min Act: -0.1700
Data Index: 571089 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.6310. Min Act: -0.1700
Data Index: 7167616 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.6310. Min Act: -0.1700
Data Index: 7811503 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 2526520 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5998. Min Act: -0.1700
Data Index: 2166832 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5998. Min Act: -0.1700
Data Index: 7957677 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 1518284 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 4684593 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5685. Min Act: -0.1700
Data Index: 4174002 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5998. Min Act: -0.1700
Data Index: 3015865 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.5373. Min Act: -0.1700
Data Index: 1514663 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.4748. Min Act: -0.1700
Data Index: 8822637 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.4123. Min Act: -0.1700
Data Index: 863060 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.3810. Min Act: -0.1700
Data Index: 8567375 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.2873. Min Act: -0.1700
Data Index: 322645 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7560. Min Range: -5.7560
Max Act: 5.2560. Min Act: -0.1700
Data Index: 4903974 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19