Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2144. Min Range: -4.2144
Max Act: 4.2144. Min Act: -0.1700
Data Index: 6438697 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.7298. Min Act: -0.1700
Data Index: 8730003 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.6672. Min Act: -0.1700
Data Index: 6980824 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.7142. Min Act: -0.1700
Data Index: 7362728 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.6046. Min Act: -0.1700
Data Index: 6699209 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5890. Min Act: -0.1700
Data Index: 5432470 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.6046. Min Act: -0.1700
Data Index: 7540253 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5733. Min Act: -0.1700
Data Index: 989579 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5420. Min Act: -0.1700
Data Index: 2166840 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5264. Min Act: -0.1700
Data Index: 6795426 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5107. Min Act: -0.1700
Data Index: 3938948 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6269361 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5420. Min Act: -0.1700
Data Index: 4284223 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5107. Min Act: -0.1700
Data Index: 6430249 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5577. Min Act: -0.1700
Data Index: 2178123 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5107. Min Act: -0.1700
Data Index: 3237700 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.5107. Min Act: -0.1700
Data Index: 3351758 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.4637. Min Act: -0.1700
Data Index: 3474733 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.4794. Min Act: -0.1700
Data Index: 1559604 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2144. Min Range: -4.2144
Max Act: 3.4480. Min Act: -0.1700
Data Index: 4859714 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19