Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0777. Min Range: -6.0777
Max Act: 6.0777. Min Act: -0.1700
Data Index: 2114609 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8902. Min Act: -0.1700
Data Index: 4683086 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8902. Min Act: -0.1700
Data Index: 7194674 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8902. Min Act: -0.1700
Data Index: 8732940 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8902. Min Act: -0.1700
Data Index: 2376941 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8590. Min Act: -0.1700
Data Index: 6010577 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8590. Min Act: -0.1700
Data Index: 3184234 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8590. Min Act: -0.1700
Data Index: 2549607 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8590. Min Act: -0.1700
Data Index: 435684 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8277. Min Act: -0.1700
Data Index: 6616376 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8277. Min Act: -0.1700
Data Index: 2549616 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8277. Min Act: -0.1700
Data Index: 4933187 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 4690895 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.8277. Min Act: -0.1700
Data Index: 3642220 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 3339550 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 5732236 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1693
Data Index: 845910 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 2766605 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 1194088 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0777. Min Range: -6.0777
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7017025 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19