Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.2024. Min Act: -0.1700
Data Index: 5086479 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1848. Min Act: -0.1700
Data Index: 4317522 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1848. Min Act: -0.1694
Data Index: 2172611 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1584. Min Act: -0.1700
Data Index: 2698313 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1497. Min Act: -0.1700
Data Index: 1461509 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1321. Min Act: -0.1700
Data Index: 8481963 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1321. Min Act: -0.1700
Data Index: 1461508 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1233. Min Act: -0.1699
Data Index: 492358 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1145. Min Act: -0.1700
Data Index: 6887833 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1233. Min Act: -0.1700
Data Index: 5062337 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1145. Min Act: -0.1700
Data Index: 6158103 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.1058. Min Act: -0.1700
Data Index: 4158125 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0970. Min Act: -0.1700
Data Index: 6158094 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0970. Min Act: -0.1700
Data Index: 5062335 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0970. Min Act: -0.1700
Data Index: 5610132 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0883. Min Act: -0.1700
Data Index: 6208418 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0970. Min Act: -0.1699
Data Index: 4089539 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0620. Min Act: -0.1700
Data Index: 6225540 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0620. Min Act: -0.1700
Data Index: 5062332 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2024. Min Range: -1.2024
Max Act: 1.0620. Min Act: -0.1700
Data Index: 1040238 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19