Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.4007. Min Act: -0.1700
Data Index: 7100624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.3382. Min Act: -0.1700
Data Index: 5067765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.3382. Min Act: -0.1700
Data Index: 7333848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.3070. Min Act: -0.1700
Data Index: 8449952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2757. Min Act: -0.1700
Data Index: 894017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2757. Min Act: -0.1700
Data Index: 2324284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2757. Min Act: -0.1700
Data Index: 733637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2757. Min Act: -0.1700
Data Index: 6333180 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 1243724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 3406351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 2090355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 8574379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 4992174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 950048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 6075810 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 1414672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 803857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2445. Min Act: -0.1700
Data Index: 5937464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2132. Min Act: -0.1700
Data Index: 2156137 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4007. Min Range: -5.4007
Max Act: 5.2132. Min Act: -0.1700
Data Index: 5859685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19