Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.2859. Min Act: -0.1700
Data Index: 29258 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0046. Min Act: -0.1700
Data Index: 8280173 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0046. Min Act: -0.1700
Data Index: 377184 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9734. Min Act: -0.1700
Data Index: 4580699 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9421. Min Act: -0.1700
Data Index: 3538898 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9421. Min Act: -0.1700
Data Index: 6398353 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8952. Min Act: -0.1700
Data Index: 3835833 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8796. Min Act: -0.1700
Data Index: 7042230 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8796. Min Act: -0.1700
Data Index: 1470510 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8639. Min Act: -0.1700
Data Index: 4310204 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5974208 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8483. Min Act: -0.1700
Data Index: 3439101 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8483. Min Act: -0.1700
Data Index: 7054638 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8483. Min Act: -0.1700
Data Index: 515515 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8327. Min Act: -0.1700
Data Index: 4029935 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8014. Min Act: -0.1700
Data Index: 5777976 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.8014. Min Act: -0.1700
Data Index: 2543884 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.7857. Min Act: -0.1700
Data Index: 3820133 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.7857. Min Act: -0.1700
Data Index: 8094152 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.7701. Min Act: -0.1700
Data Index: 3608113 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19