Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.8121. Min Act: -0.1700
Data Index: 7838713 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.8035. Min Act: -0.1700
Data Index: 3511692 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7518. Min Act: -0.1699
Data Index: 3145198 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7518. Min Act: -0.1696
Data Index: 8311771 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7431. Min Act: -0.1596
Data Index: 2547613 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7259. Min Act: -0.1689
Data Index: 5847983 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7345. Min Act: -0.1699
Data Index: 2484579 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7172. Min Act: -0.1529
Data Index: 2477577 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7259. Min Act: -0.1699
Data Index: 1478531 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7259. Min Act: -0.1700
Data Index: 3980401 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7172. Min Act: -0.1661
Data Index: 5990485 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7085. Min Act: -0.1506
Data Index: 7843155 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7172. Min Act: -0.1699
Data Index: 4091424 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7172. Min Act: -0.1700
Data Index: 6011877 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7085. Min Act: -0.1691
Data Index: 3352214 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7172. Min Act: -0.1700
Data Index: 861352 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7085. Min Act: -0.1677
Data Index: 5820924 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7085. Min Act: -0.1700
Data Index: 7861024 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.7085. Min Act: -0.1700
Data Index: 1715574 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8121. Min Range: -1.8121
Max Act: 1.6999. Min Act: -0.1700
Data Index: 3920294 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19