Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 909 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.8506. Min Act: -0.1700
Data Index: 3294103 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.7567. Min Act: -0.1700
Data Index: 6225934 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6942. Min Act: -0.1700
Data Index: 2285443 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.7255. Min Act: -0.1700
Data Index: 7265851 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6942. Min Act: -0.1700
Data Index: 3867066 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6629. Min Act: -0.1700
Data Index: 5956014 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6629. Min Act: -0.1700
Data Index: 133620 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 7156430 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6629. Min Act: -0.1700
Data Index: 7136738 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 796064 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6629. Min Act: -0.1700
Data Index: 133621 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 436024 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 3676169 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 4755903 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 3152097 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6003. Min Act: -0.1700
Data Index: 7615279 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 7863554 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6316. Min Act: -0.1700
Data Index: 6469387 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6629. Min Act: -0.1700
Data Index: 6268298 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8506. Min Range: -3.8506
Max Act: 3.6003. Min Act: -0.1700
Data Index: 5507027 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19