Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.6444. Min Act: -0.1700
Data Index: 1236071 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.5662. Min Act: -0.1700
Data Index: 539858 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.5505. Min Act: -0.1700
Data Index: 2808874 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.5505. Min Act: -0.1700
Data Index: 2854215 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4879. Min Act: -0.1700
Data Index: 1465165 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.5036. Min Act: -0.1700
Data Index: 2463794 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4879. Min Act: -0.1700
Data Index: 6309765 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4722. Min Act: -0.1700
Data Index: 6700928 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4566. Min Act: -0.1700
Data Index: 6551778 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4252. Min Act: -0.1700
Data Index: 3240542 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4409. Min Act: -0.1700
Data Index: 4026249 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4252. Min Act: -0.1700
Data Index: 864452 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5794421 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4095. Min Act: -0.1700
Data Index: 1725356 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4095. Min Act: -0.1700
Data Index: 7141904 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4095. Min Act: -0.1700
Data Index: 6256565 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.3939. Min Act: -0.1700
Data Index: 5879608 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.4095. Min Act: -0.1700
Data Index: 5309468 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.3782. Min Act: -0.1700
Data Index: 763996 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6444. Min Range: -3.6444
Max Act: 3.3939. Min Act: -0.1700
Data Index: 6215558 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19