Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.1937. Min Act: -0.1700
Data Index: 1370282 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.0796. Min Act: -0.1700
Data Index: 8555236 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.0447. Min Act: -0.1698
Data Index: 8262992 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.0273. Min Act: -0.1700
Data Index: 381244 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.0186. Min Act: -0.1700
Data Index: 2354006 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1937. Min Range: -1.1937
Max Act: 1.0186. Min Act: -0.1699
Data Index: 7564839 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9925. Min Act: -0.1700
Data Index: 7846003 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9752. Min Act: -0.1697
Data Index: 1632052 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9752. Min Act: -0.1700
Data Index: 5747672 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9752. Min Act: -0.1700
Data Index: 533165 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9665. Min Act: -0.1700
Data Index: 2366121 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9579. Min Act: -0.1699
Data Index: 5435258 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9665. Min Act: -0.1700
Data Index: 6435882 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9665. Min Act: -0.1700
Data Index: 6514055 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9579. Min Act: -0.1700
Data Index: 7549334 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9407. Min Act: -0.1699
Data Index: 1811070 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9407. Min Act: -0.1700
Data Index: 1241339 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9235. Min Act: -0.1700
Data Index: 4974981 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9149. Min Act: -0.1700
Data Index: 6549825 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1937. Min Range: -1.1937
Max Act: 0.9149. Min Act: -0.1700
Data Index: 4232433 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19