Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 90 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1800. Min Range: -4.1800
Max Act: 4.1800. Min Act: -0.1700
Data Index: 1157237 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1800. Min Range: -4.1800
Max Act: 4.0081. Min Act: -0.1700
Data Index: 829875 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.9299. Min Act: -0.1700
Data Index: 434870 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.8673. Min Act: -0.1700
Data Index: 1426086 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.8517. Min Act: -0.1700
Data Index: 191865 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.8517. Min Act: -0.1700
Data Index: 413126 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.8048. Min Act: -0.1700
Data Index: 264863 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.8048. Min Act: -0.1700
Data Index: 200501 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.7891. Min Act: -0.1700
Data Index: 1587264 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.7266. Min Act: -0.1700
Data Index: 1276294 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6953. Min Act: -0.1700
Data Index: 1290789 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6796. Min Act: -0.1700
Data Index: 996407 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6483. Min Act: -0.1700
Data Index: 593949 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6640. Min Act: -0.1700
Data Index: 526197 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6796. Min Act: -0.1700
Data Index: 1061028 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6483. Min Act: -0.1700
Data Index: 847663 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6327. Min Act: -0.1700
Data Index: 427793 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6796. Min Act: -0.1700
Data Index: 27855 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6327. Min Act: -0.1700
Data Index: 1309532 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1800. Min Range: -4.1800
Max Act: 3.6327. Min Act: -0.1700
Data Index: 441485 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19