Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0778. Min Range: -7.0778
Max Act: 7.0778. Min Act: -0.1700
Data Index: 2010231 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.8903. Min Act: -0.1700
Data Index: 8713487 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.9216. Min Act: -0.1700
Data Index: 684162 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7966. Min Act: -0.1700
Data Index: 938263 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7966. Min Act: -0.1700
Data Index: 2236541 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7341. Min Act: -0.1700
Data Index: 5015804 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7653. Min Act: -0.1700
Data Index: 5116094 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7028. Min Act: -0.1700
Data Index: 4658973 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.7028. Min Act: -0.1700
Data Index: 4320429 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6716. Min Act: -0.1700
Data Index: 5039360 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6403. Min Act: -0.1700
Data Index: 686713 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6716. Min Act: -0.1700
Data Index: 7761871 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6091. Min Act: -0.1700
Data Index: 1873232 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6403. Min Act: -0.1700
Data Index: 6494844 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6091. Min Act: -0.1700
Data Index: 4606434 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6091. Min Act: -0.1700
Data Index: 4663655 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7771503 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.5778. Min Act: -0.1700
Data Index: 4597012 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.5778. Min Act: -0.1700
Data Index: 5855412 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0778. Min Range: -7.0778
Max Act: 6.5778. Min Act: -0.1700
Data Index: 2287363 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19