Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1686 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3382. Min Range: -4.3382
Max Act: 4.3382. Min Act: -0.1698
Data Index: 306920 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3382. Min Range: -4.3382
Max Act: 4.1038. Min Act: -0.1700
Data Index: 1194007 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3382. Min Range: -4.3382
Max Act: 4.0569. Min Act: -0.1694
Data Index: 1351925 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3382. Min Range: -4.3382
Max Act: 4.0413. Min Act: -0.1700
Data Index: 1114878 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.9631. Min Act: -0.1700
Data Index: 1299387 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.9787. Min Act: -0.1700
Data Index: 554575 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.9631. Min Act: -0.1698
Data Index: 1032027 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.9475. Min Act: -0.1698
Data Index: 1003105 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8849. Min Act: -0.1700
Data Index: 1241928 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8849. Min Act: -0.1674
Data Index: 1217190 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.9162. Min Act: -0.1698
Data Index: 1053650 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1645
Data Index: 92730 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1153
Data Index: 466486 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8693. Min Act: -0.1700
Data Index: 1158366 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1700
Data Index: 237987 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1651
Data Index: 830539 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1700
Data Index: 1178225 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8380. Min Act: -0.1578
Data Index: 361396 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8380. Min Act: -0.1700
Data Index: 1241627 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3382. Min Range: -4.3382
Max Act: 3.8536. Min Act: -0.1684
Data Index: 765722 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19