Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 509 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.8954. Min Act: -0.1700
Data Index: 149954 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.6454. Min Act: -0.1700
Data Index: 997274 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.5829. Min Act: -0.1700
Data Index: 1058176 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.3329. Min Act: -0.1700
Data Index: 1495997 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1559927 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1484759 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1297987 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.2079. Min Act: -0.1700
Data Index: 286170 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1145218 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1766. Min Act: -0.1700
Data Index: 876387 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 499037 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1036480 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1115831 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 621184 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1505836 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.1141. Min Act: -0.1700
Data Index: 1647324 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.0828. Min Act: -0.1700
Data Index: 171932 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.0203. Min Act: -0.1700
Data Index: 1343098 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.0516. Min Act: -0.1700
Data Index: 982694 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8954. Min Range: -4.8954
Max Act: 4.0203. Min Act: -0.1700
Data Index: 902036 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19