Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 700 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.1640. Min Act: -0.1700
Data Index: 1582807 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0702. Min Act: -0.1700
Data Index: 634646 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0702. Min Act: -0.1700
Data Index: 679872 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0389. Min Act: -0.1700
Data Index: 293407 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0389. Min Act: -0.1700
Data Index: 998899 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0389. Min Act: -0.1700
Data Index: 1506340 (Python Code)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0389. Min Act: -0.1700
Data Index: 787772 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0076. Min Act: -0.1700
Data Index: 974707 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0076. Min Act: -0.1700
Data Index: 984220 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1640. Min Range: -4.1640
Max Act: 4.0076. Min Act: -0.1700
Data Index: 1087469 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9764. Min Act: -0.1700
Data Index: 1609600 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9764. Min Act: -0.1700
Data Index: 1429473 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 323337 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9764. Min Act: -0.1700
Data Index: 1026403 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 473394 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 1461759 (Python Code)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 1522546 (Python Code)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 1486155 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9138. Min Act: -0.1700
Data Index: 1044025 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1640. Min Range: -4.1640
Max Act: 3.9451. Min Act: -0.1700
Data Index: 1097274 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19