Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5725. Min Range: -9.5725
Max Act: 9.5725. Min Act: -0.1700
Data Index: 6693098 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.4787. Min Act: -0.1700
Data Index: 5580452 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.4787. Min Act: -0.1698
Data Index: 3541733 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.4475. Min Act: -0.1700
Data Index: 6587731 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.2912. Min Act: -0.1700
Data Index: 2782155 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.2600. Min Act: -0.1700
Data Index: 375552 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.2287. Min Act: -0.1700
Data Index: 4536916 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.2287. Min Act: -0.1698
Data Index: 4135356 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.1662. Min Act: -0.1700
Data Index: 5408965 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.1037. Min Act: -0.1698
Data Index: 1854877 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.0725. Min Act: -0.1700
Data Index: 5030124 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.0725. Min Act: -0.1698
Data Index: 7417006 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.0100. Min Act: -0.1700
Data Index: 6623825 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5725. Min Range: -9.5725
Max Act: 8.0725. Min Act: -0.1700
Data Index: 1822802 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9787. Min Act: -0.1698
Data Index: 6716383 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9787. Min Act: -0.1700
Data Index: 7438608 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9475. Min Act: -0.1698
Data Index: 2875136 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9162. Min Act: -0.1700
Data Index: 2996826 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9475. Min Act: -0.1698
Data Index: 4186951 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5725. Min Range: -9.5725
Max Act: 7.9162. Min Act: -0.1700
Data Index: 3346968 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19