Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0725. Min Act: -0.1700
Data Index: 7515084 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0410. Min Act: -0.1700
Data Index: 6479139 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0567. Min Act: -0.1700
Data Index: 8251259 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0410. Min Act: -0.1700
Data Index: 3524872 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0094. Min Act: -0.1700
Data Index: 462929 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0725. Min Range: -3.0725
Max Act: 3.0094. Min Act: -0.1700
Data Index: 4488959 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.9619. Min Act: -0.1700
Data Index: 6395411 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.9144. Min Act: -0.1700
Data Index: 3085749 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1678156 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8986. Min Act: -0.1700
Data Index: 5098076 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.9144. Min Act: -0.1700
Data Index: 8269301 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8986. Min Act: -0.1700
Data Index: 4390534 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8986. Min Act: -0.1700
Data Index: 2121584 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8827. Min Act: -0.1700
Data Index: 5495362 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8510. Min Act: -0.1700
Data Index: 408527 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8351. Min Act: -0.1700
Data Index: 7942388 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8510. Min Act: -0.1700
Data Index: 688817 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8192. Min Act: -0.1700
Data Index: 8706830 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8351. Min Act: -0.1700
Data Index: 8736467 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0725. Min Range: -3.0725
Max Act: 2.8351. Min Act: -0.1700
Data Index: 200570 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19