Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.2143. Min Act: -0.1700
Data Index: 5018754 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2143. Min Range: -5.2143
Max Act: 5.1205. Min Act: -0.1700
Data Index: 6365812 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9955. Min Act: -0.1700
Data Index: 2329976 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 6616848 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9643. Min Act: -0.1700
Data Index: 1298168 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9330. Min Act: -0.1700
Data Index: 790374 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.9018. Min Act: -0.1700
Data Index: 4678573 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8393. Min Act: -0.1700
Data Index: 8038491 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8705. Min Act: -0.1700
Data Index: 2983156 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8705. Min Act: -0.1700
Data Index: 5800153 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8393. Min Act: -0.1700
Data Index: 6424600 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8393. Min Act: -0.1700
Data Index: 6862781 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8080. Min Act: -0.1700
Data Index: 4943976 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7768. Min Act: -0.1700
Data Index: 4681269 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.8080. Min Act: -0.1700
Data Index: 5117571 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7768. Min Act: -0.1700
Data Index: 1861229 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7455. Min Act: -0.1700
Data Index: 5591104 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4684110 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4761261 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2143. Min Range: -5.2143
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4875861 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19