Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.6015. Min Act: -0.1700
Data Index: 364145 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.5858. Min Act: -0.1700
Data Index: 3077730 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.5075. Min Act: -0.1700
Data Index: 5507073 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.5075. Min Act: -0.1700
Data Index: 3442170 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4762. Min Act: -0.1700
Data Index: 973811 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.5075. Min Act: -0.1700
Data Index: 5690101 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4919. Min Act: -0.1700
Data Index: 1459200 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4762. Min Act: -0.1700
Data Index: 4040994 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4449. Min Act: -0.1700
Data Index: 4499039 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4449. Min Act: -0.1700
Data Index: 8573393 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 6301388 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4449. Min Act: -0.1700
Data Index: 127537 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 4432009 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 6890388 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 7296049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 5561481 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.3979. Min Act: -0.1700
Data Index: 2677160 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4135. Min Act: -0.1700
Data Index: 6946771 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 1891793 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6015. Min Range: -3.6015
Max Act: 3.4292. Min Act: -0.1700
Data Index: 2063341 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19