Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 906 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.3257. Min Act: -0.1700
Data Index: 662946 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.1694. Min Act: -0.1700
Data Index: 365300 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.1694. Min Act: -0.1700
Data Index: 1217427 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.1694. Min Act: -0.1700
Data Index: 953550 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0444. Min Act: -0.1700
Data Index: 858279 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0757. Min Act: -0.1700
Data Index: 838513 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0131. Min Act: -0.1700
Data Index: 643733 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0131. Min Act: -0.1700
Data Index: 517154 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0131. Min Act: -0.1700
Data Index: 724217 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9819. Min Act: -0.1700
Data Index: 145774 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9819. Min Act: -0.1700
Data Index: 613046 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 259928 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 683915 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3257. Min Range: -4.3257
Max Act: 4.0131. Min Act: -0.1700
Data Index: 897160 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 1359448 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 468949 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 478941 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9193. Min Act: -0.1700
Data Index: 828718 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9506. Min Act: -0.1700
Data Index: 58074 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3257. Min Range: -4.3257
Max Act: 3.9193. Min Act: -0.1700
Data Index: 1004562 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19