Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 793 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.9045. Min Act: -0.1700
Data Index: 1216874 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.9204. Min Act: -0.1700
Data Index: 974031 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.9045. Min Act: -0.1700
Data Index: 632137 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.9045. Min Act: -0.1700
Data Index: 839356 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8569. Min Act: -0.1700
Data Index: 820981 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8886. Min Act: -0.1700
Data Index: 134268 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8410. Min Act: -0.1700
Data Index: 1329404 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8092. Min Act: -0.1700
Data Index: 997232 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8251. Min Act: -0.1700
Data Index: 603514 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8251. Min Act: -0.1700
Data Index: 1211182 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8251. Min Act: -0.1700
Data Index: 122818 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8251. Min Act: -0.1700
Data Index: 172952 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8410. Min Act: -0.1700
Data Index: 435718 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7614. Min Act: -0.1700
Data Index: 672806 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7773. Min Act: -0.1700
Data Index: 532460 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.8092. Min Act: -0.1700
Data Index: 1347538 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1195563 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7773. Min Act: -0.1700
Data Index: 491089 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7773. Min Act: -0.1700
Data Index: 379566 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9204. Min Range: -2.9204
Max Act: 2.7614. Min Act: -0.1700
Data Index: 220369 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19