Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.8187. Min Act: -0.1688
Data Index: 6163856 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.8187. Min Act: -0.1700
Data Index: 5475919 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.8016. Min Act: -0.1699
Data Index: 1703016 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7757. Min Act: -0.1700
Data Index: 4939233 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7843. Min Act: -0.1700
Data Index: 7888502 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7757. Min Act: -0.1700
Data Index: 4623776 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7585. Min Act: -0.1700
Data Index: 8724618 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7585. Min Act: -0.1700
Data Index: 6663432 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7585. Min Act: -0.1700
Data Index: 3673710 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7498. Min Act: -0.1700
Data Index: 1574789 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1700
Data Index: 2452299 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1700
Data Index: 2493563 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1700
Data Index: 1912149 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1700
Data Index: 1471786 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7498. Min Act: -0.1700
Data Index: 5530298 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1696
Data Index: 2110121 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7412. Min Act: -0.1700
Data Index: 6694587 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7326. Min Act: -0.1700
Data Index: 1412200 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7326. Min Act: -0.1700
Data Index: 4069571 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8187. Min Range: -1.8187
Max Act: 1.7326. Min Act: -0.1700
Data Index: 1494160 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19