Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0979. Min Act: -0.1125
Data Index: 813061 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0542. Min Act: -0.1360
Data Index: 553445 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0194. Min Act: -0.1335
Data Index: 130335 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0107. Min Act: -0.1304
Data Index: 5304010 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0107. Min Act: -0.1312
Data Index: 130333 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0979. Min Range: -1.0979
Max Act: 1.0020. Min Act: -0.1177
Data Index: 130334 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9760. Min Act: -0.1352
Data Index: 7310764 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9674. Min Act: -0.1095
Data Index: 345148 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9587. Min Act: -0.1594
Data Index: 7891124 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9674. Min Act: -0.1284
Data Index: 390498 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9415. Min Act: -0.1438
Data Index: 377253 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9501. Min Act: -0.1372
Data Index: 130319 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9501. Min Act: -0.1087
Data Index: 8069108 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9415. Min Act: -0.1335
Data Index: 4543222 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9329. Min Act: -0.1372
Data Index: 2130674 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9157. Min Act: -0.1675
Data Index: 5832300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9157. Min Act: -0.1053
Data Index: 5142150 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9157. Min Act: -0.1161
Data Index: 130332 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9157. Min Act: -0.1299
Data Index: 130336 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0979. Min Range: -1.0979
Max Act: 0.9243. Min Act: -0.1413
Data Index: 8101900 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19