Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 893 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8703. Min Act: -0.1700
Data Index: 1176178 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8703. Min Act: -0.1700
Data Index: 765123 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8390. Min Act: -0.1700
Data Index: 978979 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8078. Min Act: -0.1700
Data Index: 912238 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8078. Min Act: -0.1700
Data Index: 412356 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7765. Min Act: -0.1700
Data Index: 102546 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8078. Min Act: -0.1700
Data Index: 1230470 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8390. Min Act: -0.1700
Data Index: 1090197 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8078. Min Act: -0.1700
Data Index: 831963 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8078. Min Act: -0.1700
Data Index: 730058 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.8390. Min Act: -0.1700
Data Index: 1303994 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7765. Min Act: -0.1700
Data Index: 619364 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7765. Min Act: -0.1700
Data Index: 753170 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7453. Min Act: -0.1700
Data Index: 1816 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7765. Min Act: -0.1699
Data Index: 800361 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7765. Min Act: -0.1700
Data Index: 1309177 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7453. Min Act: -0.1700
Data Index: 800416 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7140. Min Act: -0.1700
Data Index: 334627 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7453. Min Act: -0.1700
Data Index: 927946 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8703. Min Range: -4.8703
Max Act: 4.7140. Min Act: -0.1700
Data Index: 743790 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19