Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 882 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.5803. Min Act: -0.1700
Data Index: 4776659 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.5319. Min Act: -0.1700
Data Index: 995123 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4995. Min Act: -0.1700
Data Index: 4478228 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4833. Min Act: -0.1700
Data Index: 7298497 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4833. Min Act: -0.1700
Data Index: 3179899 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4833. Min Act: -0.1700
Data Index: 1430569 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4833. Min Act: -0.1700
Data Index: 4630613 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4833. Min Act: -0.1700
Data Index: 6196172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4671. Min Act: -0.1700
Data Index: 6651695 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4671. Min Act: -0.1700
Data Index: 7760939 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4671. Min Act: -0.1700
Data Index: 1115348 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4183. Min Act: -0.1700
Data Index: 8609503 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4508. Min Act: -0.1700
Data Index: 685765 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4508. Min Act: -0.1700
Data Index: 2662466 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4346. Min Act: -0.1700
Data Index: 6222841 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4346. Min Act: -0.1700
Data Index: 826622 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4346. Min Act: -0.1700
Data Index: 7355550 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4346. Min Act: -0.1700
Data Index: 4788641 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4020. Min Act: -0.1700
Data Index: 1960206 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5803. Min Range: -2.5803
Max Act: 2.4183. Min Act: -0.1700
Data Index: 2028183 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19