Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3701. Min Act: -0.1700
Data Index: 1307134 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.4014. Min Act: -0.1700
Data Index: 6685969 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3701. Min Act: -0.1700
Data Index: 7619595 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3389. Min Act: -0.1700
Data Index: 346805 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3076. Min Act: -0.1700
Data Index: 5849824 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2764. Min Act: -0.1700
Data Index: 4597099 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3076. Min Act: -0.1700
Data Index: 3305260 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3076. Min Act: -0.1700
Data Index: 2233669 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3076. Min Act: -0.1700
Data Index: 650329 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.3076. Min Act: -0.1700
Data Index: 6732915 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2764. Min Act: -0.1700
Data Index: 5368751 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2451. Min Act: -0.1700
Data Index: 4565087 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2451. Min Act: -0.1700
Data Index: 7258903 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2764. Min Act: -0.1700
Data Index: 7840313 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6109503 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2139. Min Act: -0.1700
Data Index: 7927658 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2139. Min Act: -0.1700
Data Index: 3135258 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2139. Min Act: -0.1700
Data Index: 6729463 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2139. Min Act: -0.1700
Data Index: 3838594 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4014. Min Range: -5.4014
Max Act: 5.2139. Min Act: -0.1700
Data Index: 2439972 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19