Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3917. Min Range: -7.3917
Max Act: 7.3917. Min Act: -0.1700
Data Index: 7203659 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3917. Min Range: -7.3917
Max Act: 7.2042. Min Act: -0.1700
Data Index: 1094078 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3917. Min Range: -7.3917
Max Act: 7.1417. Min Act: -0.1700
Data Index: 2658143 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3917. Min Range: -7.3917
Max Act: 7.1104. Min Act: -0.1700
Data Index: 3297084 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3917. Min Range: -7.3917
Max Act: 7.1104. Min Act: -0.1700
Data Index: 7174620 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.9854. Min Act: -0.1700
Data Index: 8294578 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.9854. Min Act: -0.1700
Data Index: 4454015 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.9542. Min Act: -0.1700
Data Index: 2405784 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.9229. Min Act: -0.1700
Data Index: 3250250 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8917. Min Act: -0.1700
Data Index: 3498985 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8917. Min Act: -0.1700
Data Index: 1001251 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8604. Min Act: -0.1700
Data Index: 6330330 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8604. Min Act: -0.1700
Data Index: 3699963 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8604. Min Act: -0.1700
Data Index: 7844515 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8292. Min Act: -0.1700
Data Index: 6676164 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8292. Min Act: -0.1700
Data Index: 5214825 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.8292. Min Act: -0.1700
Data Index: 3350401 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.7979. Min Act: -0.1700
Data Index: 7087583 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.7979. Min Act: -0.1700
Data Index: 2164563 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3917. Min Range: -7.3917
Max Act: 6.7979. Min Act: -0.1700
Data Index: 2577636 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19