Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1303 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.6362. Min Act: -0.1700
Data Index: 922242 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.5737. Min Act: -0.1700
Data Index: 1090218 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.5112. Min Act: -0.1700
Data Index: 516880 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.5424. Min Act: -0.1700
Data Index: 990854 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4799. Min Act: -0.1700
Data Index: 173812 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4799. Min Act: -0.1700
Data Index: 1044818 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.5112. Min Act: -0.1700
Data Index: 351129 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4799. Min Act: -0.1700
Data Index: 57453 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4799. Min Act: -0.1700
Data Index: 224538 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3861. Min Act: -0.1700
Data Index: 423222 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4174. Min Act: -0.1700
Data Index: 1179976 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4487. Min Act: -0.1700
Data Index: 180984 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4487. Min Act: -0.1700
Data Index: 689330 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3861. Min Act: -0.1700
Data Index: 321843 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4174. Min Act: -0.1700
Data Index: 611467 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3861. Min Act: -0.1700
Data Index: 346704 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3549. Min Act: -0.1700
Data Index: 545859 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.4487. Min Act: -0.1700
Data Index: 258206 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3549. Min Act: -0.1700
Data Index: 347886 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6362. Min Range: -4.6362
Max Act: 4.3861. Min Act: -0.1700
Data Index: 253435 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19