Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0896. Min Range: -6.0896
Max Act: 6.0896. Min Act: -0.1700
Data Index: 4126136 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.9646. Min Act: -0.1700
Data Index: 2581072 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.9334. Min Act: -0.1700
Data Index: 8595798 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.9021. Min Act: -0.1700
Data Index: 3716311 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.9021. Min Act: -0.1700
Data Index: 4665311 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.8396. Min Act: -0.1700
Data Index: 6384168 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.8084. Min Act: -0.1700
Data Index: 7427929 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.7771. Min Act: -0.1700
Data Index: 1392183 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.7459. Min Act: -0.1700
Data Index: 222272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.7146. Min Act: -0.1700
Data Index: 3507023 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6834. Min Act: -0.1700
Data Index: 353103 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6834. Min Act: -0.1700
Data Index: 3755820 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6521. Min Act: -0.1700
Data Index: 6953492 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6521. Min Act: -0.1700
Data Index: 2548933 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6547357 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6209. Min Act: -0.1700
Data Index: 1904660 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.6521. Min Act: -0.1700
Data Index: 2957424 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.5584. Min Act: -0.1700
Data Index: 6555086 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.5271. Min Act: -0.1700
Data Index: 6492646 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0896. Min Range: -6.0896
Max Act: 5.5584. Min Act: -0.1700
Data Index: 5286550 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19