Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1969 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0550. Min Range: -4.0550
Max Act: 4.0550. Min Act: -0.1700
Data Index: 92047 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0550. Min Range: -4.0550
Max Act: 4.0550. Min Act: -0.1700
Data Index: 742188 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0550. Min Range: -4.0550
Max Act: 4.0237. Min Act: -0.1700
Data Index: 1237582 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9612. Min Act: -0.1700
Data Index: 687032 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9612. Min Act: -0.1700
Data Index: 687899 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0550. Min Range: -4.0550
Max Act: 4.0237. Min Act: -0.1700
Data Index: 14534 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9925. Min Act: -0.1700
Data Index: 1001393 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9612. Min Act: -0.1700
Data Index: 1246274 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 1232943 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 759150 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 29030 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 535881 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 482702 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 446457 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 576791 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9612. Min Act: -0.1700
Data Index: 715205 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9612. Min Act: -0.1700
Data Index: 912754 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.9299. Min Act: -0.1700
Data Index: 811097 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.8986. Min Act: -0.1700
Data Index: 617154 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0550. Min Range: -4.0550
Max Act: 3.8986. Min Act: -0.1700
Data Index: 185712 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19