Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.6062. Min Act: -0.1700
Data Index: 713696 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.5124. Min Act: -0.1700
Data Index: 500361 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.3249. Min Act: -0.1700
Data Index: 517024 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2936. Min Act: -0.1700
Data Index: 1163253 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.3249. Min Act: -0.1700
Data Index: 82373 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2311. Min Act: -0.1700
Data Index: 959156 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2624. Min Act: -0.1700
Data Index: 891865 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1999. Min Act: -0.1700
Data Index: 1031129 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2311. Min Act: -0.1700
Data Index: 592719 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2624. Min Act: -0.1700
Data Index: 1184006 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2624. Min Act: -0.1699
Data Index: 670299 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1686. Min Act: -0.1700
Data Index: 217012 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1999. Min Act: -0.1700
Data Index: 900702 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1686. Min Act: -0.1700
Data Index: 1258293 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2624. Min Act: -0.1700
Data Index: 1267437 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1999. Min Act: -0.1700
Data Index: 1264027 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1686. Min Act: -0.1700
Data Index: 76634 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.2311. Min Act: -0.1700
Data Index: 673522 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1686. Min Act: -0.1700
Data Index: 863064 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6062. Min Range: -4.6062
Max Act: 4.1686. Min Act: -0.1700
Data Index: 973496 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19