Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1039 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.8248. Min Act: -0.1700
Data Index: 284435 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.5118. Min Act: -0.1700
Data Index: 1257483 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.4492. Min Act: -0.1700
Data Index: 6173710 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.4962. Min Act: -0.1700
Data Index: 1719455 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3865. Min Act: -0.1700
Data Index: 522874 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.4178. Min Act: -0.1700
Data Index: 512060 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.4021. Min Act: -0.1700
Data Index: 6385195 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3394. Min Act: -0.1700
Data Index: 7304752 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3708. Min Act: -0.1700
Data Index: 2742018 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3394. Min Act: -0.1700
Data Index: 4053130 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3865. Min Act: -0.1700
Data Index: 8551155 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3551. Min Act: -0.1700
Data Index: 3838829 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3551. Min Act: -0.1700
Data Index: 3888100 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3394. Min Act: -0.1700
Data Index: 5228949 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.2609. Min Act: -0.1700
Data Index: 8556976 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3394. Min Act: -0.1700
Data Index: 1582101 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3394. Min Act: -0.1700
Data Index: 6385192 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3237. Min Act: -0.1700
Data Index: 1994990 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.2923. Min Act: -0.1700
Data Index: 425179 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8248. Min Range: -3.8248
Max Act: 3.3237. Min Act: -0.1700
Data Index: 2143552 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19