Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.2487. Min Act: -0.1700
Data Index: 7748697 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2487. Min Range: -5.2487
Max Act: 5.2487. Min Act: -0.1700
Data Index: 488569 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.9675. Min Act: -0.1700
Data Index: 6889580 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.9362. Min Act: -0.1700
Data Index: 8726452 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.8737. Min Act: -0.1700
Data Index: 3562260 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.8425. Min Act: -0.1700
Data Index: 5841260 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.8425. Min Act: -0.1700
Data Index: 2416690 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.8112. Min Act: -0.1700
Data Index: 3990637 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7800. Min Act: -0.1700
Data Index: 2716026 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7800. Min Act: -0.1700
Data Index: 7825207 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 707133 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 5501379 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 6326561 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 1093514 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 5115329 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 868080 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 7575448 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.7175. Min Act: -0.1700
Data Index: 7076476 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.6862. Min Act: -0.1700
Data Index: 6091995 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2487. Min Range: -5.2487
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4952612 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19