Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 68 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.7433. Min Act: -0.1700
Data Index: 1036870 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.7433. Min Act: -0.1700
Data Index: 375975 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.7745. Min Act: -0.1700
Data Index: 232066 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.7120. Min Act: -0.1700
Data Index: 987443 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.6808. Min Act: -0.1700
Data Index: 18073 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.7433. Min Act: -0.1700
Data Index: 578114 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5245. Min Act: -0.1700
Data Index: 994948 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5557. Min Act: -0.1700
Data Index: 1009568 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5557. Min Act: -0.1700
Data Index: 339984 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5245. Min Act: -0.1700
Data Index: 1295963 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5557. Min Act: -0.1700
Data Index: 745119 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.4620. Min Act: -0.1700
Data Index: 610097 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.5245. Min Act: -0.1700
Data Index: 90123 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.4307. Min Act: -0.1700
Data Index: 1040481 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.3995. Min Act: -0.1700
Data Index: 632014 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.4307. Min Act: -0.1700
Data Index: 970816 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.4307. Min Act: -0.1700
Data Index: 343655 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.3995. Min Act: -0.1700
Data Index: 1220480 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.3370. Min Act: -0.1700
Data Index: 68712 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7745. Min Range: -4.7745
Max Act: 4.3682. Min Act: -0.1700
Data Index: 278948 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19