Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.2293. Min Act: -0.1700
Data Index: 8751114 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1667. Min Act: -0.1699
Data Index: 5543599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1667. Min Act: -0.1700
Data Index: 3596584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1355. Min Act: -0.1699
Data Index: 5658669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1355. Min Act: -0.1700
Data Index: 5750670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1355. Min Act: -0.1700
Data Index: 8369568 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1042. Min Act: -0.1700
Data Index: 2074014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1042. Min Act: -0.1697
Data Index: 2977226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1042. Min Act: -0.1700
Data Index: 5769010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1923688 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.1042. Min Act: -0.1700
Data Index: 652462 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0730. Min Act: -0.1700
Data Index: 5411851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0730. Min Act: -0.1700
Data Index: 2623910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0730. Min Act: -0.1700
Data Index: 5333322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2718384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0417. Min Act: -0.1699
Data Index: 1184615 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0417. Min Act: -0.1700
Data Index: 1268581 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2248069 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0417. Min Act: -0.1700
Data Index: 4978428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2293. Min Range: -4.2293
Max Act: 4.0105. Min Act: -0.1700
Data Index: 681446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19