Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1512. Min Range: -7.1512
Max Act: 7.1512. Min Act: -0.1700
Data Index: 8674456 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.7762. Min Act: -0.1700
Data Index: 3916613 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.7762. Min Act: -0.1700
Data Index: 6692580 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.7449. Min Act: -0.1700
Data Index: 7861549 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4541258 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.6199. Min Act: -0.1700
Data Index: 3962817 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5887. Min Act: -0.1700
Data Index: 5223826 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.6199. Min Act: -0.1700
Data Index: 8209270 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5262. Min Act: -0.1700
Data Index: 3111581 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5574. Min Act: -0.1700
Data Index: 940865 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5574. Min Act: -0.1700
Data Index: 2109765 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5262. Min Act: -0.1700
Data Index: 6237532 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5262. Min Act: -0.1700
Data Index: 5658520 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5262. Min Act: -0.1700
Data Index: 7609777 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4949. Min Act: -0.1700
Data Index: 8301383 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4949. Min Act: -0.1700
Data Index: 7109358 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4637. Min Act: -0.1700
Data Index: 3293967 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4637. Min Act: -0.1700
Data Index: 1287464 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4949. Min Act: -0.1700
Data Index: 3199811 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.4637. Min Act: -0.1700
Data Index: 6541108 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19