Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 15 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9340. Min Act: -0.1700
Data Index: 493574 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9498. Min Act: -0.1700
Data Index: 809793 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0131. Min Range: -3.0131
Max Act: 3.0131. Min Act: -0.1700
Data Index: 615084 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9340. Min Act: -0.1700
Data Index: 1325254 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8546. Min Act: -0.1700
Data Index: 165679 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9340. Min Act: -0.1700
Data Index: 924240 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9023. Min Act: -0.1700
Data Index: 143098 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8546. Min Act: -0.1700
Data Index: 1239970 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8228. Min Act: -0.1700
Data Index: 629346 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8864. Min Act: -0.1700
Data Index: 642110 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8387. Min Act: -0.1700
Data Index: 821218 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8705. Min Act: -0.1700
Data Index: 155640 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8228. Min Act: -0.1700
Data Index: 1136359 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9023. Min Act: -0.1700
Data Index: 599192 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.9023. Min Act: -0.1700
Data Index: 463039 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8387. Min Act: -0.1700
Data Index: 835460 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8546. Min Act: -0.1700
Data Index: 171902 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8864. Min Act: -0.1700
Data Index: 1222421 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8864. Min Act: -0.1700
Data Index: 127124 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0131. Min Range: -3.0131
Max Act: 2.8705. Min Act: -0.1700
Data Index: 1067000 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19