Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1768 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.9222. Min Act: -0.1700
Data Index: 439728 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8587. Min Act: -0.1700
Data Index: 1121184 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8269. Min Act: -0.1700
Data Index: 1093179 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8269. Min Act: -0.1700
Data Index: 677270 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8269. Min Act: -0.1700
Data Index: 1084335 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7951. Min Act: -0.1700
Data Index: 45447 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8110. Min Act: -0.1700
Data Index: 150335 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8269. Min Act: -0.1700
Data Index: 507566 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8110. Min Act: -0.1700
Data Index: 380011 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8110. Min Act: -0.1700
Data Index: 349124 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.8110. Min Act: -0.1700
Data Index: 1265575 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7951. Min Act: -0.1700
Data Index: 19210 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7792. Min Act: -0.1700
Data Index: 396617 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7951. Min Act: -0.1700
Data Index: 1294597 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7951. Min Act: -0.1700
Data Index: 1115197 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7951. Min Act: -0.1700
Data Index: 633011 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7792. Min Act: -0.1700
Data Index: 600082 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7792. Min Act: -0.1700
Data Index: 591759 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7792. Min Act: -0.1700
Data Index: 912209 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9222. Min Range: -2.9222
Max Act: 2.7473. Min Act: -0.1700
Data Index: 892414 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19