Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.4298. Min Act: -0.1700
Data Index: 549402 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7945028 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1486. Min Act: -0.1700
Data Index: 4699656 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1798. Min Act: -0.1700
Data Index: 1971023 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1486. Min Act: -0.1700
Data Index: 5018879 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1486. Min Act: -0.1700
Data Index: 233617 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1486. Min Act: -0.1700
Data Index: 4136606 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1173. Min Act: -0.1700
Data Index: 7222375 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1486. Min Act: -0.1691
Data Index: 497466 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1173. Min Act: -0.1700
Data Index: 7906817 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1173. Min Act: -0.1700
Data Index: 2078183 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0861. Min Act: -0.1700
Data Index: 7203877 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.1173. Min Act: -0.1700
Data Index: 135413 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0548. Min Act: -0.1700
Data Index: 6282734 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0548. Min Act: -0.1699
Data Index: 6805244 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0548. Min Act: -0.1700
Data Index: 1315611 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0236. Min Act: -0.1700
Data Index: 4914676 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0236. Min Act: -0.1700
Data Index: 7985004 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0236. Min Act: -0.1700
Data Index: 5924276 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4298. Min Range: -5.4298
Max Act: 5.0236. Min Act: -0.1700
Data Index: 8607148 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19