Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2013 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.8983. Min Act: -0.1700
Data Index: 1086008 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.8824. Min Act: -0.1700
Data Index: 1083684 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.8029. Min Act: -0.1700
Data Index: 947127 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.7711. Min Act: -0.1700
Data Index: 213351 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.7391. Min Act: -0.1700
Data Index: 204303 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6912. Min Act: -0.1700
Data Index: 1044227 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6751. Min Act: -0.1700
Data Index: 1100591 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6751. Min Act: -0.1700
Data Index: 1350961 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6751. Min Act: -0.1700
Data Index: 526360 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6431. Min Act: -0.1700
Data Index: 397381 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6109. Min Act: -0.1700
Data Index: 989831 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6270. Min Act: -0.1700
Data Index: 519345 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6109. Min Act: -0.1700
Data Index: 1278935 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6109. Min Act: -0.1700
Data Index: 577520 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6109. Min Act: -0.1700
Data Index: 757893 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.5948. Min Act: -0.1700
Data Index: 1135079 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.6109. Min Act: -0.1700
Data Index: 1284873 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.5948. Min Act: -0.1700
Data Index: 727310 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.5948. Min Act: -0.1700
Data Index: 190146 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8983. Min Range: -2.8983
Max Act: 2.5948. Min Act: -0.1700
Data Index: 340677 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19