Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1363 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.2209. Min Act: -0.1700
Data Index: 1287932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.1584. Min Act: -0.1700
Data Index: 5214404 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.1272. Min Act: -0.1700
Data Index: 4868265 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.1272. Min Act: -0.1700
Data Index: 2288080 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.1584. Min Act: -0.1700
Data Index: 3329227 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 8204010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1814173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1278660 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 7952479 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 4491294 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 5102628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 1696410 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 4949283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 819272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 4590559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 3376497 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 1131242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 7196563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 4521749 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2209. Min Range: -5.2209
Max Act: 5.0647. Min Act: -0.1700
Data Index: 5552623 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19