Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.3320. Min Act: -0.1700
Data Index: 7743199 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.1132. Min Act: -0.1700
Data Index: 1794116 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.0507. Min Act: -0.1700
Data Index: 4771745 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.0507. Min Act: -0.1700
Data Index: 621690 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.0820. Min Act: -0.1700
Data Index: 1413434 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.0194. Min Act: -0.1700
Data Index: 5453922 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3320. Min Range: -4.3320
Max Act: 4.0194. Min Act: -0.1700
Data Index: 4526068 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9569. Min Act: -0.1700
Data Index: 6895403 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9569. Min Act: -0.1700
Data Index: 7515441 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9257. Min Act: -0.1700
Data Index: 2897818 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9257. Min Act: -0.1700
Data Index: 5379834 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9257. Min Act: -0.1700
Data Index: 8541417 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9100. Min Act: -0.1700
Data Index: 3106166 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8944. Min Act: -0.1700
Data Index: 4486344 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.9100. Min Act: -0.1700
Data Index: 7013150 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8944. Min Act: -0.1700
Data Index: 3358170 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8944. Min Act: -0.1700
Data Index: 822482 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8631. Min Act: -0.1700
Data Index: 175136 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8944. Min Act: -0.1700
Data Index: 2478081 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3320. Min Range: -4.3320
Max Act: 3.8944. Min Act: -0.1700
Data Index: 3679948 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19