Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1787 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.4857. Min Act: -0.1700
Data Index: 32559 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.4545. Min Act: -0.1700
Data Index: 332950 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.4232. Min Act: -0.1700
Data Index: 1204535 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3919. Min Act: -0.1700
Data Index: 1113481 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3919. Min Act: -0.1700
Data Index: 243831 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3607. Min Act: -0.1700
Data Index: 1298817 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2982. Min Act: -0.1700
Data Index: 377176 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3138. Min Act: -0.1700
Data Index: 872923 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3451. Min Act: -0.1700
Data Index: 964350 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2826. Min Act: -0.1700
Data Index: 606845 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3607. Min Act: -0.1700
Data Index: 799572 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2826. Min Act: -0.1700
Data Index: 549447 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3294. Min Act: -0.1700
Data Index: 883183 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3607. Min Act: -0.1700
Data Index: 823159 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3138. Min Act: -0.1700
Data Index: 874320 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2982. Min Act: -0.1700
Data Index: 1297257 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.3138. Min Act: -0.1700
Data Index: 24068 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2982. Min Act: -0.1700
Data Index: 1052584 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2513. Min Act: -0.1700
Data Index: 1041089 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4857. Min Range: -4.4857
Max Act: 4.2826. Min Act: -0.1700
Data Index: 194060 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19