Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 16 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.3744. Min Act: -0.1700
Data Index: 963843 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.3432. Min Act: -0.1700
Data Index: 6155 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.3119. Min Act: -0.1700
Data Index: 270141 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2807. Min Act: -0.1700
Data Index: 755961 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2182. Min Act: -0.1700
Data Index: 80301 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2494. Min Act: -0.1700
Data Index: 123521 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2494. Min Act: -0.1700
Data Index: 1316758 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2182. Min Act: -0.1700
Data Index: 99019 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.2807. Min Act: -0.1700
Data Index: 901746 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 106594 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1869. Min Act: -0.1700
Data Index: 245951 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 857344 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 189984 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.0932. Min Act: -0.1700
Data Index: 1063 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 1105689 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1557. Min Act: -0.1700
Data Index: 529774 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1557. Min Act: -0.1700
Data Index: 1112765 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.0619. Min Act: -0.1700
Data Index: 1161052 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.0932. Min Act: -0.1700
Data Index: 102337 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3744. Min Range: -6.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 603578 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19