Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.5759. Min Act: -0.1700
Data Index: 1273819 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.2634. Min Act: -0.1700
Data Index: 5774757 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.2322. Min Act: -0.1700
Data Index: 1605788 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.0759. Min Act: -0.1700
Data Index: 6544446 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.0447. Min Act: -0.1700
Data Index: 5976183 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.0447. Min Act: -0.1700
Data Index: 7466344 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.0447. Min Act: -0.1700
Data Index: 7228790 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5759. Min Range: -6.5759
Max Act: 6.0134. Min Act: -0.1700
Data Index: 3288050 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9822. Min Act: -0.1700
Data Index: 7172457 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9822. Min Act: -0.1700
Data Index: 8696207 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9509. Min Act: -0.1700
Data Index: 2881024 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9509. Min Act: -0.1700
Data Index: 4213571 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9509. Min Act: -0.1700
Data Index: 1685218 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9509. Min Act: -0.1700
Data Index: 7572981 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9197. Min Act: -0.1700
Data Index: 6677782 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9509. Min Act: -0.1700
Data Index: 4098628 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9197. Min Act: -0.1700
Data Index: 7375513 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9197. Min Act: -0.1700
Data Index: 1364361 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9197. Min Act: -0.1700
Data Index: 7104383 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5759. Min Range: -6.5759
Max Act: 5.9197. Min Act: -0.1700
Data Index: 3998022 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19