Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 284 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.6076. Min Act: -0.1700
Data Index: 45193 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.3889. Min Act: -0.1700
Data Index: 946360 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.1701. Min Act: -0.1700
Data Index: 346256 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.0764. Min Act: -0.1700
Data Index: 898740 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6076. Min Range: -6.6076
Max Act: 6.0139. Min Act: -0.1700
Data Index: 495129 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.9514. Min Act: -0.1700
Data Index: 239488 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8576. Min Act: -0.1700
Data Index: 374031 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.9201. Min Act: -0.1700
Data Index: 659310 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7951. Min Act: -0.1700
Data Index: 1340896 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.8576. Min Act: -0.1700
Data Index: 894397 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7639. Min Act: -0.1700
Data Index: 816504 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7951. Min Act: -0.1700
Data Index: 170854 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6701. Min Act: -0.1700
Data Index: 652596 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6389. Min Act: -0.1700
Data Index: 861515 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7014. Min Act: -0.1700
Data Index: 252671 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6389. Min Act: -0.1700
Data Index: 968596 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6389. Min Act: -0.1700
Data Index: 140726 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7014. Min Act: -0.1700
Data Index: 735895 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.7326. Min Act: -0.1700
Data Index: 1109243 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6076. Min Range: -6.6076
Max Act: 5.6389. Min Act: -0.1700
Data Index: 1219905 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19