Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9908. Min Act: -0.1700
Data Index: 1216947 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9595. Min Act: -0.1700
Data Index: 762466 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9595. Min Act: -0.1700
Data Index: 1352224 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9282. Min Act: -0.1700
Data Index: 1288342 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9595. Min Act: -0.1700
Data Index: 930601 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.9595. Min Act: -0.1700
Data Index: 1218297 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8970. Min Act: -0.1700
Data Index: 1152126 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8970. Min Act: -0.1700
Data Index: 1052054 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8657. Min Act: -0.1700
Data Index: 336497 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8657. Min Act: -0.1700
Data Index: 1167353 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8970. Min Act: -0.1700
Data Index: 706382 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8657. Min Act: -0.1700
Data Index: 857072 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8657. Min Act: -0.1700
Data Index: 878848 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8344. Min Act: -0.1700
Data Index: 78169 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8031. Min Act: -0.1700
Data Index: 1358815 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8344. Min Act: -0.1700
Data Index: 615281 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8031. Min Act: -0.1700
Data Index: 1159381 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8031. Min Act: -0.1700
Data Index: 1231570 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.8031. Min Act: -0.1700
Data Index: 1218352 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9908. Min Range: -3.9908
Max Act: 3.7718. Min Act: -0.1700
Data Index: 524460 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19