Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.9296. Min Act: -0.1700
Data Index: 6936196 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.7109. Min Act: -0.1700
Data Index: 1267467 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.5859. Min Act: -0.1700
Data Index: 8230296 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.5546. Min Act: -0.1700
Data Index: 390671 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.5234. Min Act: -0.1700
Data Index: 7912105 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.4921. Min Act: -0.1700
Data Index: 381631 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.3046. Min Act: -0.1700
Data Index: 2977118 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2734. Min Act: -0.1700
Data Index: 7420049 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2734. Min Act: -0.1700
Data Index: 4191048 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2734. Min Act: -0.1700
Data Index: 7610838 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2734. Min Act: -0.1700
Data Index: 5927292 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2421. Min Act: -0.1700
Data Index: 6154163 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2109. Min Act: -0.1700
Data Index: 7499018 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2421. Min Act: -0.1700
Data Index: 6548173 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.1796. Min Act: -0.1700
Data Index: 2218132 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2109. Min Act: -0.1700
Data Index: 3757249 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.2421. Min Act: -0.1700
Data Index: 6008880 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.1484. Min Act: -0.1700
Data Index: 4143697 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.1484. Min Act: -0.1700
Data Index: 214271 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9296. Min Range: -7.9296
Max Act: 7.1171. Min Act: -0.1700
Data Index: 5908424 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19