Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1679 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.4091. Min Act: -0.1700
Data Index: 4766669 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.3778. Min Act: -0.1700
Data Index: 2101613 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.3153. Min Act: -0.1700
Data Index: 5885358 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.3153. Min Act: -0.1700
Data Index: 8770828 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2840. Min Act: -0.1700
Data Index: 8540884 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2528. Min Act: -0.1700
Data Index: 680697 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2528. Min Act: -0.1700
Data Index: 6328782 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2215. Min Act: -0.1700
Data Index: 1669836 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2215. Min Act: -0.1700
Data Index: 7896316 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1903. Min Act: -0.1700
Data Index: 2297489 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.2215. Min Act: -0.1700
Data Index: 1497266 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1903. Min Act: -0.1700
Data Index: 4840855 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 7936154 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 7232446 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 6678879 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 3939739 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 8568906 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1903. Min Act: -0.1700
Data Index: 5386570 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1590. Min Act: -0.1700
Data Index: 4580592 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4091. Min Range: -4.4091
Max Act: 4.1278. Min Act: -0.1700
Data Index: 4973160 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19