Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4500 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2625. Min Range: -6.2625
Max Act: 6.2625. Min Act: -0.1700
Data Index: 4714329 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2625. Min Range: -6.2625
Max Act: 6.2625. Min Act: -0.1700
Data Index: 4420728 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2625. Min Range: -6.2625
Max Act: 6.1375. Min Act: -0.1700
Data Index: 8758850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2625. Min Range: -6.2625
Max Act: 6.1062. Min Act: -0.1700
Data Index: 8063234 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2625. Min Range: -6.2625
Max Act: 6.0125. Min Act: -0.1700
Data Index: 7703049 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.9812. Min Act: -0.1700
Data Index: 7013158 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.9500. Min Act: -0.1700
Data Index: 2466140 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.8875. Min Act: -0.1700
Data Index: 3750340 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.8562. Min Act: -0.1700
Data Index: 2363850 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.8250. Min Act: -0.1700
Data Index: 2673929 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.8250. Min Act: -0.1700
Data Index: 3565939 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7937. Min Act: -0.1700
Data Index: 8462765 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7625. Min Act: -0.1700
Data Index: 3553944 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7625. Min Act: -0.1700
Data Index: 7186995 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1997660 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7312. Min Act: -0.1700
Data Index: 6262741 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7312. Min Act: -0.1700
Data Index: 1604703 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7312. Min Act: -0.1700
Data Index: 8396517 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7625. Min Act: -0.1700
Data Index: 5352619 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2625. Min Range: -6.2625
Max Act: 5.7000. Min Act: -0.1700
Data Index: 2472530 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19