Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 138 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.2096. Min Act: -0.1700
Data Index: 1199060 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.1158. Min Act: -0.1700
Data Index: 826241 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.1158. Min Act: -0.1700
Data Index: 1257600 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.1471. Min Act: -0.1700
Data Index: 1034889 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.1471. Min Act: -0.1700
Data Index: 1062629 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0845. Min Act: -0.1700
Data Index: 422173 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.1158. Min Act: -0.1700
Data Index: 120652 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0220. Min Act: -0.1700
Data Index: 444480 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0220. Min Act: -0.1700
Data Index: 804226 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9908. Min Act: -0.1700
Data Index: 1318900 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0220. Min Act: -0.1700
Data Index: 878125 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0533. Min Act: -0.1700
Data Index: 776248 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0220. Min Act: -0.1700
Data Index: 590467 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9908. Min Act: -0.1700
Data Index: 484739 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9908. Min Act: -0.1700
Data Index: 1282730 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9908. Min Act: -0.1700
Data Index: 22333 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2096. Min Range: -4.2096
Max Act: 4.0533. Min Act: -0.1700
Data Index: 425194 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9908. Min Act: -0.1700
Data Index: 309429 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9282. Min Act: -0.1700
Data Index: 696914 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2096. Min Range: -4.2096
Max Act: 3.9595. Min Act: -0.1700
Data Index: 927005 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19