Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1862 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0501. Min Range: -3.0501
Max Act: 3.0501. Min Act: -0.1700
Data Index: 1423850 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.9236. Min Act: -0.1700
Data Index: 1065790 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8919. Min Act: -0.1700
Data Index: 193548 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.9077. Min Act: -0.1700
Data Index: 924508 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8760. Min Act: -0.1700
Data Index: 1027984 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8283. Min Act: -0.1700
Data Index: 181469 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8283. Min Act: -0.1700
Data Index: 1449860 (Python Code)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8124. Min Act: -0.1700
Data Index: 1339083 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.8124. Min Act: -0.1700
Data Index: 991123 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.7965. Min Act: -0.1700
Data Index: 423634 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.7806. Min Act: -0.1700
Data Index: 265589 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.7486. Min Act: -0.1700
Data Index: 978275 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.7486. Min Act: -0.1700
Data Index: 681439 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.7007. Min Act: -0.1700
Data Index: 1153962 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6847. Min Act: -0.1700
Data Index: 1109781 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6847. Min Act: -0.1700
Data Index: 1551446 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6687. Min Act: -0.1700
Data Index: 1007448 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6687. Min Act: -0.1700
Data Index: 1261324 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6526. Min Act: -0.1700
Data Index: 1283997 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0501. Min Range: -3.0501
Max Act: 2.6526. Min Act: -0.1700
Data Index: 148363 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19