Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4130 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2208. Min Range: -5.2208
Max Act: 5.2208. Min Act: -0.1700
Data Index: 2730282 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.9083. Min Act: -0.1700
Data Index: 8150624 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.9083. Min Act: -0.1700
Data Index: 6113984 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.8458. Min Act: -0.1700
Data Index: 945074 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.8458. Min Act: -0.1700
Data Index: 2302587 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.7208. Min Act: -0.1700
Data Index: 7557035 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6896. Min Act: -0.1700
Data Index: 6193301 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6896. Min Act: -0.1700
Data Index: 412816 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 8155730 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 6644569 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 7512600 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 7775646 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 7758506 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 5368948 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.5958. Min Act: -0.1700
Data Index: 6654436 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 1949670 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.6271. Min Act: -0.1700
Data Index: 8217026 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.5646. Min Act: -0.1700
Data Index: 7432884 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.5958. Min Act: -0.1700
Data Index: 8075933 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2208. Min Range: -5.2208
Max Act: 4.5958. Min Act: -0.1700
Data Index: 2387727 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19