Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 985 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.6040. Min Act: -0.1700
Data Index: 560622 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.5880. Min Act: -0.1700
Data Index: 448343 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.5234. Min Act: -0.1700
Data Index: 981940 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.5072. Min Act: -0.1700
Data Index: 54428 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.5072. Min Act: -0.1700
Data Index: 185578 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4910. Min Act: -0.1700
Data Index: 1080806 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4910. Min Act: -0.1700
Data Index: 36772 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 1018166 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 787709 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 354339 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 1225944 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 845501 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 889537 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4748. Min Act: -0.1700
Data Index: 193959 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4423. Min Act: -0.1700
Data Index: 1130589 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4423. Min Act: -0.1700
Data Index: 868828 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4586. Min Act: -0.1700
Data Index: 413805 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4586. Min Act: -0.1700
Data Index: 1107967 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4586. Min Act: -0.1699
Data Index: 203031 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6040. Min Range: -2.6040
Max Act: 2.4586. Min Act: -0.1700
Data Index: 101117 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19