Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 981 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1121845 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.4864. Min Act: -0.1700
Data Index: 875225 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.4551. Min Act: -0.1700
Data Index: 113784 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 533979 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 160178 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 1347961 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 665470 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 966761 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2989. Min Act: -0.1699
Data Index: 46114 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2989. Min Act: -0.1700
Data Index: 704702 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 8069 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 1268835 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.3301. Min Act: -0.1700
Data Index: 570744 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2989. Min Act: -0.1699
Data Index: 355379 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 832576 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1626
Data Index: 417339 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2364. Min Act: -0.1700
Data Index: 322442 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2676. Min Act: -0.1700
Data Index: 374806 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2364. Min Act: -0.1699
Data Index: 1211748 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5801. Min Range: -4.5801
Max Act: 4.2051. Min Act: -0.1700
Data Index: 1025063 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19