Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2033 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.4115. Min Act: -0.1700
Data Index: 8033061 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.4115. Min Act: -0.1700
Data Index: 454638 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.4427. Min Act: -0.1700
Data Index: 1700590 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2865. Min Act: -0.1700
Data Index: 2201293 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2865. Min Act: -0.1700
Data Index: 4858918 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2865. Min Act: -0.1700
Data Index: 5117098 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2865. Min Act: -0.1700
Data Index: 1698235 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2552. Min Act: -0.1700
Data Index: 1946806 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2552. Min Act: -0.1700
Data Index: 1716378 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2552. Min Act: -0.1700
Data Index: 1950635 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 722912 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 1086625 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 7878339 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 5577539 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 1045680 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2240. Min Act: -0.1700
Data Index: 3820291 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2552. Min Act: -0.1700
Data Index: 7321370 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4093508 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1927. Min Act: -0.1700
Data Index: 3553229 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1927. Min Act: -0.1700
Data Index: 904437 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19