Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2305219 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.2774. Min Act: -0.1700
Data Index: 8630629 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3298283 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.0899. Min Act: -0.1700
Data Index: 3589664 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3399. Min Range: -5.3399
Max Act: 5.0899. Min Act: -0.1700
Data Index: 4653485 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.9337. Min Act: -0.1700
Data Index: 1095416 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.9337. Min Act: -0.1700
Data Index: 7913116 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.9649. Min Act: -0.1700
Data Index: 8764078 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8399. Min Act: -0.1700
Data Index: 6590565 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8399. Min Act: -0.1700
Data Index: 2320841 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8087. Min Act: -0.1700
Data Index: 3233061 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8087. Min Act: -0.1700
Data Index: 7370311 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8087. Min Act: -0.1700
Data Index: 8035163 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.8087. Min Act: -0.1700
Data Index: 2376797 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7774. Min Act: -0.1700
Data Index: 5742405 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7462. Min Act: -0.1700
Data Index: 6115291 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7774. Min Act: -0.1700
Data Index: 1353568 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7774. Min Act: -0.1700
Data Index: 8724406 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7774. Min Act: -0.1700
Data Index: 3511937 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3399. Min Range: -5.3399
Max Act: 4.7774. Min Act: -0.1700
Data Index: 3739137 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19