Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.6750. Min Act: -0.1700
Data Index: 7772781 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.6750. Min Act: -0.1700
Data Index: 7856987 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.5187. Min Act: -0.1700
Data Index: 8548468 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4875. Min Act: -0.1700
Data Index: 7504896 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4562. Min Act: -0.1700
Data Index: 3013272 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 7282785 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 1191551 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 942775 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 3895067 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.4250. Min Act: -0.1700
Data Index: 618179 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 4349027 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 7177309 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 6865030 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 6622974 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 6079423 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 8194254 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3312. Min Act: -0.1700
Data Index: 388812 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 510302 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 1005228 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 7260119 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19