Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.2308. Min Act: -0.1700
Data Index: 1943492 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1837. Min Act: -0.1700
Data Index: 335047 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1522. Min Act: -0.1700
Data Index: 2031433 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1679. Min Act: -0.1700
Data Index: 1943491 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1207. Min Act: -0.1700
Data Index: 2713961 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1207. Min Act: -0.1700
Data Index: 8395264 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.1050. Min Act: -0.1700
Data Index: 209030 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0892. Min Act: -0.1700
Data Index: 7528604 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 3595564 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0734. Min Act: -0.1700
Data Index: 8165982 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 161182 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 3117526 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 4923528 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 2918944 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 6538560 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0734. Min Act: -0.1700
Data Index: 7197415 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0576. Min Act: -0.1700
Data Index: 3117525 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0419. Min Act: -0.1700
Data Index: 8289614 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2308. Min Range: -3.2308
Max Act: 2.9945. Min Act: -0.1700
Data Index: 4117612 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2308. Min Range: -3.2308
Max Act: 3.0261. Min Act: -0.1700
Data Index: 661898 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19