Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5398 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.7854. Min Act: -0.1699
Data Index: 1010828 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.7542. Min Act: -0.1700
Data Index: 3415073 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.7229. Min Act: -0.1700
Data Index: 5369805 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.7229. Min Act: -0.1700
Data Index: 3250390 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.7229. Min Act: -0.1700
Data Index: 7198633 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.6604. Min Act: -0.1700
Data Index: 7980192 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.5979. Min Act: -0.1700
Data Index: 5234522 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.5979. Min Act: -0.1700
Data Index: 1412281 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.5042. Min Act: -0.1700
Data Index: 7242913 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.5042. Min Act: -0.1700
Data Index: 4599828 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4729. Min Act: -0.1700
Data Index: 4960636 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.5042. Min Act: -0.1700
Data Index: 1295918 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4104. Min Act: -0.1700
Data Index: 3590131 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4417. Min Act: -0.1700
Data Index: 4892010 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4417. Min Act: -0.1700
Data Index: 5512041 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4104. Min Act: -0.1700
Data Index: 8515064 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4104. Min Act: -0.1700
Data Index: 812275 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4417. Min Act: -0.1700
Data Index: 2209630 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4104. Min Act: -0.1700
Data Index: 5790051 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7854. Min Range: -6.7854
Max Act: 6.4104. Min Act: -0.1700
Data Index: 6783777 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19