Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4562 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3512. Min Range: -8.3512
Max Act: 8.3512. Min Act: -0.1700
Data Index: 7273647 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3512. Min Range: -8.3512
Max Act: 8.1012. Min Act: -0.1700
Data Index: 7790724 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3512. Min Range: -8.3512
Max Act: 8.1637. Min Act: -0.1700
Data Index: 4461795 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3512. Min Range: -8.3512
Max Act: 8.1012. Min Act: -0.1700
Data Index: 2096480 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.9762. Min Act: -0.1700
Data Index: 2246312 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.9137. Min Act: -0.1700
Data Index: 8155681 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 524352 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 4128002 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 2285391 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8512. Min Act: -0.1700
Data Index: 4400951 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8199. Min Act: -0.1700
Data Index: 174335 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8199. Min Act: -0.1700
Data Index: 2695934 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.8199. Min Act: -0.1700
Data Index: 1469914 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.7887. Min Act: -0.1700
Data Index: 2024187 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.7887. Min Act: -0.1700
Data Index: 5597649 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.7887. Min Act: -0.1700
Data Index: 6261717 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.6949. Min Act: -0.1700
Data Index: 8350047 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.6949. Min Act: -0.1700
Data Index: 1949557 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.6637. Min Act: -0.1700
Data Index: 4734069 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3512. Min Range: -8.3512
Max Act: 7.6949. Min Act: -0.1700
Data Index: 3884741 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19