Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1252 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0846. Min Range: -5.0846
Max Act: 5.0846. Min Act: -0.1700
Data Index: 7400841 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0846. Min Range: -5.0846
Max Act: 5.0221. Min Act: -0.1700
Data Index: 667523 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0846. Min Range: -5.0846
Max Act: 5.0221. Min Act: -0.1700
Data Index: 2318550 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.8658. Min Act: -0.1700
Data Index: 2658607 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.8346. Min Act: -0.1700
Data Index: 3174046 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.8033. Min Act: -0.1700
Data Index: 7832793 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.8033. Min Act: -0.1700
Data Index: 7449683 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7721. Min Act: -0.1700
Data Index: 8293576 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7408. Min Act: -0.1700
Data Index: 5038754 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 6159635 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 5224010 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 1530382 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 5393570 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 1870628 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7408. Min Act: -0.1700
Data Index: 184593 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 7312409 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.6783. Min Act: -0.1700
Data Index: 5224005 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.7096. Min Act: -0.1700
Data Index: 6713175 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.6783. Min Act: -0.1700
Data Index: 7181059 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0846. Min Range: -5.0846
Max Act: 4.6783. Min Act: -0.1700
Data Index: 5728168 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19