Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.8691. Min Act: -0.1700
Data Index: 7875802 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.8005. Min Act: -0.1700
Data Index: 6673254 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.7833. Min Act: -0.1700
Data Index: 2149708 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.7660. Min Act: -0.1700
Data Index: 6673255 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.7488. Min Act: -0.1700
Data Index: 1782561 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6968. Min Act: -0.1700
Data Index: 4527773 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6795. Min Act: -0.1700
Data Index: 505293 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6621. Min Act: -0.1700
Data Index: 969958 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6621. Min Act: -0.1700
Data Index: 3967519 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6621. Min Act: -0.1700
Data Index: 7131877 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6447. Min Act: -0.1700
Data Index: 3359702 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6447. Min Act: -0.1700
Data Index: 6851013 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 8398815 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 5431610 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 4628632 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.5924. Min Act: -0.1700
Data Index: 242289 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 1895379 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 3414395 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.6098. Min Act: -0.1700
Data Index: 2712919 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8691. Min Range: -1.8691
Max Act: 1.5924. Min Act: -0.1700
Data Index: 5339157 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19