Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0304. Min Range: -6.0304
Max Act: 6.0304. Min Act: -0.1700
Data Index: 7598846 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9992. Min Act: -0.1700
Data Index: 8653585 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9992. Min Act: -0.1700
Data Index: 939178 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9367. Min Act: -0.1700
Data Index: 844951 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9679. Min Act: -0.1700
Data Index: 7197589 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 7498214 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9367. Min Act: -0.1700
Data Index: 936072 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 4153152 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 7411060 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 3770600 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 1959521 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 3360656 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9367. Min Act: -0.1700
Data Index: 5402349 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8742. Min Act: -0.1700
Data Index: 794713 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8742. Min Act: -0.1700
Data Index: 5790204 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8429. Min Act: -0.1700
Data Index: 5704058 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.9054. Min Act: -0.1700
Data Index: 3696724 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8742. Min Act: -0.1700
Data Index: 5608560 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8742. Min Act: -0.1700
Data Index: 7253985 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0304. Min Range: -6.0304
Max Act: 5.8429. Min Act: -0.1700
Data Index: 1067505 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19