Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2230 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0679. Min Act: -0.1700
Data Index: 5542633 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0679. Min Act: -0.1700
Data Index: 7889905 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0366. Min Act: -0.1700
Data Index: 5649881 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0366. Min Act: -0.1700
Data Index: 5252492 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0679. Min Range: -4.0679
Max Act: 4.0054. Min Act: -0.1700
Data Index: 8160537 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9428. Min Act: -0.1700
Data Index: 2400117 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9428. Min Act: -0.1700
Data Index: 6269434 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9428. Min Act: -0.1700
Data Index: 898652 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9116. Min Act: -0.1700
Data Index: 6977802 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9116. Min Act: -0.1700
Data Index: 3160613 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9116. Min Act: -0.1700
Data Index: 2766545 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8803. Min Act: -0.1700
Data Index: 789675 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9116. Min Act: -0.1700
Data Index: 8268248 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.9428. Min Act: -0.1700
Data Index: 455955 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8803. Min Act: -0.1700
Data Index: 4316277 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8803. Min Act: -0.1700
Data Index: 162548 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8490. Min Act: -0.1700
Data Index: 8683434 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1632674 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8803. Min Act: -0.1700
Data Index: 6702688 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0679. Min Range: -4.0679
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3876958 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19