Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.8669. Min Act: -0.1700
Data Index: 6762117 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.8044. Min Act: -0.1700
Data Index: 5683654 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.7106. Min Act: -0.1700
Data Index: 4123832 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6794. Min Act: -0.1700
Data Index: 19283 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6794. Min Act: -0.1700
Data Index: 510744 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6794. Min Act: -0.1700
Data Index: 6127586 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6794. Min Act: -0.1700
Data Index: 4672455 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6481. Min Act: -0.1700
Data Index: 812277 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6169. Min Act: -0.1700
Data Index: 4899863 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.6169. Min Act: -0.1700
Data Index: 1232821 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5544. Min Act: -0.1700
Data Index: 1654803 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5231. Min Act: -0.1700
Data Index: 7083617 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5856. Min Act: -0.1700
Data Index: 1768045 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5856. Min Act: -0.1700
Data Index: 6380275 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5544. Min Act: -0.1700
Data Index: 4733218 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5544. Min Act: -0.1700
Data Index: 4051447 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.4919. Min Act: -0.1700
Data Index: 3721432 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5544. Min Act: -0.1700
Data Index: 8175338 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5231. Min Act: -0.1700
Data Index: 7658071 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8669. Min Range: -6.8669
Max Act: 6.5231. Min Act: -0.1700
Data Index: 1895386 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19