Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4671. Min Act: -0.1700
Data Index: 2911330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 4177556 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 3794236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 4687864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 774236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 3790106 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 8535913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4357. Min Act: -0.1700
Data Index: 524219 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 3467602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.3730. Min Act: -0.1700
Data Index: 6180893 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7658418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.3730. Min Act: -0.1700
Data Index: 5495861 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7695295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7953389 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 4469342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 1242882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 373331 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 1211710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.4044. Min Act: -0.1700
Data Index: 5316285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4671. Min Range: -3.4671
Max Act: 3.3730. Min Act: -0.1700
Data Index: 371130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19