Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 155 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.9859. Min Act: -0.1700
Data Index: 1766121 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.6422. Min Act: -0.1700
Data Index: 1211572 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.3609. Min Act: -0.1700
Data Index: 3091115 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.3609. Min Act: -0.1700
Data Index: 179185 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.3297. Min Act: -0.1700
Data Index: 4447771 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.2672. Min Act: -0.1700
Data Index: 6671678 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.2359. Min Act: -0.1700
Data Index: 3230788 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.1734. Min Act: -0.1700
Data Index: 4234890 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.1734. Min Act: -0.1700
Data Index: 2795885 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.1422. Min Act: -0.1700
Data Index: 1606195 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9859. Min Range: -7.9859
Max Act: 7.0484. Min Act: -0.1700
Data Index: 6630022 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.9859. Min Act: -0.1700
Data Index: 8363970 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.9547. Min Act: -0.1700
Data Index: 7996405 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.9234. Min Act: -0.1700
Data Index: 7163498 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7681371 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.7984. Min Act: -0.1700
Data Index: 6573968 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.7672. Min Act: -0.1700
Data Index: 5446444 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.7672. Min Act: -0.1700
Data Index: 8050372 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.7047. Min Act: -0.1700
Data Index: 8808051 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9859. Min Range: -7.9859
Max Act: 6.6734. Min Act: -0.1700
Data Index: 1975895 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19