Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.8992. Min Act: -0.1700
Data Index: 5261715 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.5242. Min Act: -0.1700
Data Index: 867577 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.4617. Min Act: -0.1700
Data Index: 4291727 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.0867. Min Act: -0.1700
Data Index: 2101853 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.1179. Min Act: -0.1700
Data Index: 4464182 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8992. Min Range: -8.8992
Max Act: 8.0554. Min Act: -0.1700
Data Index: 1804330 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9929. Min Act: -0.1700
Data Index: 8595138 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9929. Min Act: -0.1700
Data Index: 4110059 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9929. Min Act: -0.1700
Data Index: 5175414 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9304. Min Act: -0.1700
Data Index: 8818942 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9617. Min Act: -0.1700
Data Index: 1192800 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9617. Min Act: -0.1700
Data Index: 4477638 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9304. Min Act: -0.1700
Data Index: 8595140 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9304. Min Act: -0.1700
Data Index: 570486 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.9617. Min Act: -0.1700
Data Index: 4464186 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.8679. Min Act: -0.1700
Data Index: 6892108 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.8679. Min Act: -0.1700
Data Index: 8315609 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.8992. Min Act: -0.1700
Data Index: 98827 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.8367. Min Act: -0.1700
Data Index: 4562784 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8992. Min Range: -8.8992
Max Act: 7.8054. Min Act: -0.1700
Data Index: 5381259 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19