Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1836 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.7342. Min Act: -0.1700
Data Index: 1018381 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6542. Min Act: -0.1700
Data Index: 1331152 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6702. Min Act: -0.1700
Data Index: 988160 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6702. Min Act: -0.1700
Data Index: 920608 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6542. Min Act: -0.1700
Data Index: 184370 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6862. Min Act: -0.1700
Data Index: 829712 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6220. Min Act: -0.1700
Data Index: 808296 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6542. Min Act: -0.1700
Data Index: 45850 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6220. Min Act: -0.1700
Data Index: 31629 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6862. Min Act: -0.1700
Data Index: 1146778 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6220. Min Act: -0.1700
Data Index: 123921 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6381. Min Act: -0.1700
Data Index: 823370 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6220. Min Act: -0.1700
Data Index: 966 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.5899. Min Act: -0.1700
Data Index: 1299029 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.5899. Min Act: -0.1700
Data Index: 650186 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6060. Min Act: -0.1700
Data Index: 231919 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.5576. Min Act: -0.1700
Data Index: 959817 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6381. Min Act: -0.1700
Data Index: 416254 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.5899. Min Act: -0.1700
Data Index: 495859 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7342. Min Range: -2.7342
Max Act: 2.6220. Min Act: -0.1700
Data Index: 938882 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19