Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5462. Min Act: -0.1700
Data Index: 6296519 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5775. Min Act: -0.1700
Data Index: 6045415 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5775. Min Act: -0.1700
Data Index: 80637 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5462. Min Act: -0.1700
Data Index: 4233930 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5462. Min Act: -0.1700
Data Index: 5403784 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5150. Min Act: -0.1700
Data Index: 4778386 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5150. Min Act: -0.1700
Data Index: 8160526 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.5150. Min Act: -0.1700
Data Index: 8339336 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 2688771 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4837. Min Act: -0.1700
Data Index: 1875234 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4837. Min Act: -0.1700
Data Index: 1221334 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4212. Min Act: -0.1700
Data Index: 7586880 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4837. Min Act: -0.1700
Data Index: 5798776 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 6572354 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4212. Min Act: -0.1700
Data Index: 1875235 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 4480144 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 3004158 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 4907843 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4525. Min Act: -0.1700
Data Index: 2048260 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5775. Min Range: -5.5775
Max Act: 5.4212. Min Act: -0.1700
Data Index: 4873930 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19