Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1968 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.9889. Min Act: -0.1700
Data Index: 1210488 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.9256. Min Act: -0.1700
Data Index: 472580 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.8462. Min Act: -0.1700
Data Index: 1054939 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.8462. Min Act: -0.1700
Data Index: 916503 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.8462. Min Act: -0.1700
Data Index: 580259 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.8303. Min Act: -0.1700
Data Index: 380478 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7985. Min Act: -0.1700
Data Index: 1194862 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7985. Min Act: -0.1700
Data Index: 346865 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7985. Min Act: -0.1700
Data Index: 448228 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7985. Min Act: -0.1700
Data Index: 989528 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7825. Min Act: -0.1700
Data Index: 24968 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7666. Min Act: -0.1700
Data Index: 184579 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7666. Min Act: -0.1700
Data Index: 27529 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7506. Min Act: -0.1700
Data Index: 679065 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7506. Min Act: -0.1700
Data Index: 314597 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7506. Min Act: -0.1700
Data Index: 1193413 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7187. Min Act: -0.1700
Data Index: 1284507 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7187. Min Act: -0.1700
Data Index: 1022866 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7187. Min Act: -0.1700
Data Index: 746777 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9889. Min Range: -2.9889
Max Act: 2.7027. Min Act: -0.1700
Data Index: 934209 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19