Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.9427. Min Act: -0.1700
Data Index: 2287220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.9114. Min Act: -0.1700
Data Index: 8531172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.9114. Min Act: -0.1700
Data Index: 3847550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.8489. Min Act: -0.1698
Data Index: 8350861 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.8489. Min Act: -0.1700
Data Index: 5093247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.8177. Min Act: -0.1697
Data Index: 4297487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.8177. Min Act: -0.1700
Data Index: 8516872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.7864. Min Act: -0.1700
Data Index: 7342296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.7551. Min Act: -0.1699
Data Index: 1684390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.7551. Min Act: -0.1700
Data Index: 3779635 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6926. Min Act: -0.1700
Data Index: 518134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6926. Min Act: -0.1700
Data Index: 5703109 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6301. Min Act: -0.1700
Data Index: 3311280 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6614. Min Act: -0.1697
Data Index: 7901440 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6301. Min Act: -0.1700
Data Index: 796689 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6301. Min Act: -0.1700
Data Index: 4671963 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.5989. Min Act: -0.1700
Data Index: 7605352 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.5989. Min Act: -0.1700
Data Index: 5814089 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.6301. Min Act: -0.1700
Data Index: 610058 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9427. Min Range: -4.9427
Max Act: 4.5676. Min Act: -0.1700
Data Index: 1765192 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19