Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 242 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.4075. Min Act: -0.1700
Data Index: 507355 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2825. Min Act: -0.1700
Data Index: 1196402 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2825. Min Act: -0.1700
Data Index: 808114 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.3138. Min Act: -0.1700
Data Index: 820619 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.3138. Min Act: -0.1700
Data Index: 617208 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2825. Min Act: -0.1700
Data Index: 1253058 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.3138. Min Act: -0.1700
Data Index: 264592 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.3138. Min Act: -0.1700
Data Index: 105222 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.1888. Min Act: -0.1700
Data Index: 824996 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1180098 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2513. Min Act: -0.1700
Data Index: 885908 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1332131 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1245213 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2513. Min Act: -0.1700
Data Index: 560927 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1168270 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.1888. Min Act: -0.1700
Data Index: 19104 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2200. Min Act: -0.1700
Data Index: 1302843 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.2200. Min Act: -0.1700
Data Index: 64379 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.1888. Min Act: -0.1700
Data Index: 430398 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4075. Min Range: -4.4075
Max Act: 4.1888. Min Act: -0.1700
Data Index: 1011303 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19