Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1118 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.3212. Min Range: -5.3212
Max Act: 5.3212. Min Act: -0.1700
Data Index: 373159 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.9150. Min Act: -0.1700
Data Index: 153426 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.8525. Min Act: -0.1700
Data Index: 1092691 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.8525. Min Act: -0.1700
Data Index: 435679 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.7900. Min Act: -0.1700
Data Index: 1277055 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.7587. Min Act: -0.1700
Data Index: 66248 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.7275. Min Act: -0.1700
Data Index: 939485 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.7275. Min Act: -0.1700
Data Index: 500167 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.7275. Min Act: -0.1700
Data Index: 649052 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 60853 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6962. Min Act: -0.1700
Data Index: 643815 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 450983 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 870377 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 962720 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6650. Min Act: -0.1700
Data Index: 973499 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 134660 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 167993 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 356518 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6337. Min Act: -0.1700
Data Index: 10725 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3212. Min Range: -5.3212
Max Act: 4.6025. Min Act: -0.1700
Data Index: 774502 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19