Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2018 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0141. Min Range: -3.0141
Max Act: 3.0141. Min Act: -0.1700
Data Index: 913518 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9825. Min Act: -0.1700
Data Index: 1079699 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9666. Min Act: -0.1700
Data Index: 422601 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9508. Min Act: -0.1700
Data Index: 774818 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9350. Min Act: -0.1700
Data Index: 510425 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9350. Min Act: -0.1700
Data Index: 688661 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9033. Min Act: -0.1700
Data Index: 1277938 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9033. Min Act: -0.1700
Data Index: 1330288 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.9191. Min Act: -0.1700
Data Index: 665080 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8715. Min Act: -0.1700
Data Index: 662119 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8715. Min Act: -0.1700
Data Index: 386579 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8556. Min Act: -0.1700
Data Index: 974646 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8398. Min Act: -0.1700
Data Index: 944155 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8079. Min Act: -0.1700
Data Index: 1165343 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8238. Min Act: -0.1700
Data Index: 656553 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8398. Min Act: -0.1700
Data Index: 111036 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.8398. Min Act: -0.1700
Data Index: 1250300 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.7920. Min Act: -0.1700
Data Index: 1174440 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.7920. Min Act: -0.1700
Data Index: 65746 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0141. Min Range: -3.0141
Max Act: 2.7920. Min Act: -0.1700
Data Index: 289592 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19