Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.8201. Min Act: -0.1700
Data Index: 7784687 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.7263. Min Act: -0.1700
Data Index: 139908 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.6951. Min Act: -0.1700
Data Index: 7464631 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.6326. Min Act: -0.1700
Data Index: 4276723 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1377549 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.6013. Min Act: -0.1700
Data Index: 8115720 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.5701. Min Act: -0.1700
Data Index: 7947705 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.5701. Min Act: -0.1700
Data Index: 6509973 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.5701. Min Act: -0.1700
Data Index: 6874768 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.5076. Min Act: -0.1700
Data Index: 5738877 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.4763. Min Act: -0.1700
Data Index: 4871330 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3826. Min Act: -0.1700
Data Index: 5927122 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3826. Min Act: -0.1700
Data Index: 7786653 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3826. Min Act: -0.1700
Data Index: 8730437 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3826. Min Act: -0.1700
Data Index: 5742384 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3826. Min Act: -0.1700
Data Index: 2514307 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3513. Min Act: -0.1700
Data Index: 8544537 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3513. Min Act: -0.1700
Data Index: 2661885 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3513. Min Act: -0.1700
Data Index: 5640087 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8201. Min Range: -7.8201
Max Act: 7.3513. Min Act: -0.1700
Data Index: 6613816 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19