Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.6556. Min Act: -0.1700
Data Index: 6214771 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.6556. Min Act: -0.1700
Data Index: 1612407 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.6243. Min Act: -0.1700
Data Index: 6214773 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.5304. Min Act: -0.1700
Data Index: 6486632 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.5147. Min Act: -0.1700
Data Index: 1761006 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4991. Min Act: -0.1700
Data Index: 3824737 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4677. Min Act: -0.1700
Data Index: 8076095 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4364. Min Act: -0.1700
Data Index: 8630549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4677. Min Act: -0.1700
Data Index: 6400226 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 5116303 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4207. Min Act: -0.1700
Data Index: 7068799 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4207. Min Act: -0.1700
Data Index: 2399992 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4207. Min Act: -0.1700
Data Index: 8666811 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 753488 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 2510476 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 2212835 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 7178131 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.4050. Min Act: -0.1700
Data Index: 1672454 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.3894. Min Act: -0.1700
Data Index: 5550130 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6556. Min Range: -3.6556
Max Act: 3.3894. Min Act: -0.1700
Data Index: 8630545 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19