Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.5113. Min Act: -0.1700
Data Index: 5759286 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.3550. Min Act: -0.1700
Data Index: 5972894 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.2613. Min Act: -0.1700
Data Index: 5637248 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.1050. Min Act: -0.1700
Data Index: 2680061 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.0738. Min Act: -0.1700
Data Index: 6588831 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5113. Min Range: -7.5113
Max Act: 7.0425. Min Act: -0.1700
Data Index: 431559 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.9488. Min Act: -0.1700
Data Index: 5670241 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.9488. Min Act: -0.1700
Data Index: 8191879 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.9175. Min Act: -0.1700
Data Index: 6691612 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.9175. Min Act: -0.1700
Data Index: 2033677 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.8550. Min Act: -0.1700
Data Index: 8132047 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.8550. Min Act: -0.1700
Data Index: 17150 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7925. Min Act: -0.1700
Data Index: 6178515 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7613. Min Act: -0.1700
Data Index: 6957658 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7613. Min Act: -0.1700
Data Index: 4700796 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7613. Min Act: -0.1700
Data Index: 303800 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7300. Min Act: -0.1700
Data Index: 677942 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7613. Min Act: -0.1700
Data Index: 3224657 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.7300. Min Act: -0.1700
Data Index: 3525340 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5113. Min Range: -7.5113
Max Act: 6.6988. Min Act: -0.1700
Data Index: 3762793 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19