Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.4542. Min Act: -0.1700
Data Index: 6728428 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.3917. Min Act: -0.1700
Data Index: 4065044 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.3604. Min Act: -0.1700
Data Index: 1510751 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.2979. Min Act: -0.1700
Data Index: 4676372 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.2667. Min Act: -0.1700
Data Index: 685797 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.2354. Min Act: -0.1700
Data Index: 457116 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2850692 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1417. Min Act: -0.1700
Data Index: 3988029 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1417. Min Act: -0.1700
Data Index: 7550936 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1104. Min Act: -0.1700
Data Index: 4491043 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1104. Min Act: -0.1700
Data Index: 7873801 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1104. Min Act: -0.1700
Data Index: 525271 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.1104. Min Act: -0.1700
Data Index: 1356795 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0792. Min Act: -0.1700
Data Index: 2746567 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0792. Min Act: -0.1700
Data Index: 3986874 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0792. Min Act: -0.1700
Data Index: 2830463 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0479. Min Act: -0.1700
Data Index: 266372 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0479. Min Act: -0.1700
Data Index: 7469398 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0479. Min Act: -0.1700
Data Index: 3488334 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4542. Min Range: -5.4542
Max Act: 5.0479. Min Act: -0.1700
Data Index: 2497741 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19