Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.4342. Min Act: -0.1700
Data Index: 4630298 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.2779. Min Act: -0.1700
Data Index: 4376813 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.0904. Min Act: -0.1700
Data Index: 4705275 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.0279. Min Act: -0.1700
Data Index: 3795748 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.0592. Min Act: -0.1700
Data Index: 5573253 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.0279. Min Act: -0.1700
Data Index: 14171 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4342. Min Range: -6.4342
Max Act: 6.0279. Min Act: -0.1700
Data Index: 1790234 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9654. Min Act: -0.1699
Data Index: 7284830 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9654. Min Act: -0.1696
Data Index: 2248626 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1700
Data Index: 4656986 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1700
Data Index: 2336486 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9342. Min Act: -0.1700
Data Index: 4670607 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9342. Min Act: -0.1700
Data Index: 2717076 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.8717. Min Act: -0.1698
Data Index: 5691189 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1700
Data Index: 4069086 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1700
Data Index: 3737343 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1700
Data Index: 4794634 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9029. Min Act: -0.1696
Data Index: 7224465 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.9342. Min Act: -0.1700
Data Index: 4520402 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4342. Min Range: -6.4342
Max Act: 5.8717. Min Act: -0.1700
Data Index: 2400374 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19