Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.2336. Min Act: -0.1700
Data Index: 359516 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.2024. Min Act: -0.1700
Data Index: 1228213 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.1086. Min Act: -0.1700
Data Index: 284880 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.1086. Min Act: -0.1700
Data Index: 297181 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.1086. Min Act: -0.1700
Data Index: 676632 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0461. Min Act: -0.1700
Data Index: 502381 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0774. Min Act: -0.1700
Data Index: 1271304 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1051982 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0461. Min Act: -0.1700
Data Index: 1278898 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1319254 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0148. Min Act: -0.1700
Data Index: 600437 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9836. Min Act: -0.1700
Data Index: 507321 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9836. Min Act: -0.1700
Data Index: 712285 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9523. Min Act: -0.1700
Data Index: 63482 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1020570 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9836. Min Act: -0.1700
Data Index: 1032050 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2336. Min Range: -4.2336
Max Act: 4.0148. Min Act: -0.1700
Data Index: 735152 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9836. Min Act: -0.1700
Data Index: 1047405 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9836. Min Act: -0.1700
Data Index: 564316 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2336. Min Range: -4.2336
Max Act: 3.9523. Min Act: -0.1700
Data Index: 572301 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19