Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0402. Min Range: -7.0402
Max Act: 7.0402. Min Act: -0.1700
Data Index: 3345200 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.9777. Min Act: -0.1700
Data Index: 1144923 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.7902. Min Act: -0.1700
Data Index: 8435336 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.7277. Min Act: -0.1700
Data Index: 5575900 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.7277. Min Act: -0.1700
Data Index: 6630880 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6965. Min Act: -0.1700
Data Index: 4053400 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6965. Min Act: -0.1700
Data Index: 5193130 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6965. Min Act: -0.1700
Data Index: 4027408 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6340. Min Act: -0.1700
Data Index: 4580379 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6340. Min Act: -0.1700
Data Index: 1000517 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6340. Min Act: -0.1700
Data Index: 5663918 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 5929207 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 8463229 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 7327363 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 2796970 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 3280932 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5715. Min Act: -0.1700
Data Index: 5927200 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.6027. Min Act: -0.1700
Data Index: 8274209 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5402. Min Act: -0.1700
Data Index: 2698940 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0402. Min Range: -7.0402
Max Act: 6.5402. Min Act: -0.1700
Data Index: 5867148 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19