Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1579 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0365. Min Range: -4.0365
Max Act: 4.0365. Min Act: -0.1700
Data Index: 1328346 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0365. Min Range: -4.0365
Max Act: 4.0365. Min Act: -0.1700
Data Index: 782488 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.9740. Min Act: -0.1700
Data Index: 865211 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.9427. Min Act: -0.1700
Data Index: 707689 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8489. Min Act: -0.1700
Data Index: 976629 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8801. Min Act: -0.1700
Data Index: 244846 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8801. Min Act: -0.1700
Data Index: 1138104 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8801. Min Act: -0.1700
Data Index: 551 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.9114. Min Act: -0.1700
Data Index: 269488 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8801. Min Act: -0.1700
Data Index: 275268 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8489. Min Act: -0.1700
Data Index: 1287225 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8489. Min Act: -0.1700
Data Index: 183751 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8489. Min Act: -0.1700
Data Index: 686812 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8489. Min Act: -0.1700
Data Index: 1090687 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8801. Min Act: -0.1700
Data Index: 156008 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8176. Min Act: -0.1700
Data Index: 1300607 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.7863. Min Act: -0.1700
Data Index: 681203 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.7863. Min Act: -0.1700
Data Index: 1180397 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8176. Min Act: -0.1700
Data Index: 565900 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0365. Min Range: -4.0365
Max Act: 3.8176. Min Act: -0.1700
Data Index: 91620 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19