Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2041 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0945. Min Range: -4.0945
Max Act: 4.0945. Min Act: -0.1700
Data Index: 993118 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.7505. Min Act: -0.1700
Data Index: 294219 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6879. Min Act: -0.1700
Data Index: 172218 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6879. Min Act: -0.1700
Data Index: 167430 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6566. Min Act: -0.1700
Data Index: 788827 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5940. Min Act: -0.1700
Data Index: 941814 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6253. Min Act: -0.1700
Data Index: 1310393 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6097. Min Act: -0.1700
Data Index: 439176 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.6253. Min Act: -0.1700
Data Index: 734216 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5940. Min Act: -0.1700
Data Index: 867403 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5784. Min Act: -0.1700
Data Index: 30980 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5940. Min Act: -0.1700
Data Index: 886898 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5940. Min Act: -0.1700
Data Index: 501730 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5784. Min Act: -0.1700
Data Index: 1072997 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5627. Min Act: -0.1700
Data Index: 421230 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5784. Min Act: -0.1700
Data Index: 60875 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5940. Min Act: -0.1700
Data Index: 781391 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5470. Min Act: -0.1700
Data Index: 384286 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5470. Min Act: -0.1700
Data Index: 242056 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0945. Min Range: -4.0945
Max Act: 3.5470. Min Act: -0.1700
Data Index: 998858 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19