Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.4509. Min Act: -0.1700
Data Index: 6472531 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.3884. Min Act: -0.1700
Data Index: 8374691 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.3884. Min Act: -0.1700
Data Index: 2795609 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.2947. Min Act: -0.1700
Data Index: 2098154 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.2322. Min Act: -0.1700
Data Index: 5882956 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.2009. Min Act: -0.1700
Data Index: 4301575 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.1697. Min Act: -0.1700
Data Index: 4984127 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0759. Min Act: -0.1700
Data Index: 8446555 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0447. Min Act: -0.1700
Data Index: 8175539 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0759. Min Act: -0.1700
Data Index: 815643 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0759. Min Act: -0.1700
Data Index: 5057281 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0447. Min Act: -0.1700
Data Index: 3198419 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4509. Min Range: -7.4509
Max Act: 7.0134. Min Act: -0.1700
Data Index: 5469753 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9822. Min Act: -0.1700
Data Index: 468634 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 8508415 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 2607473 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 5830266 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 2607479 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 2607470 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4509. Min Range: -7.4509
Max Act: 6.9197. Min Act: -0.1700
Data Index: 537500 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19