Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2013 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.7079. Min Act: -0.1700
Data Index: 1607345 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.5671. Min Act: -0.1700
Data Index: 437457 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4887. Min Act: -0.1700
Data Index: 389175 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4417. Min Act: -0.1700
Data Index: 1623799 (Python Code)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4260. Min Act: -0.1700
Data Index: 1408187 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4417. Min Act: -0.1700
Data Index: 1574383 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4260. Min Act: -0.1700
Data Index: 1573084 (Python Code)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4260. Min Act: -0.1700
Data Index: 1488695 (Python Code)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4103. Min Act: -0.1700
Data Index: 1656886 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4103. Min Act: -0.1700
Data Index: 1410346 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.4103. Min Act: -0.1700
Data Index: 1403567 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3790. Min Act: -0.1700
Data Index: 1655575 (Python Code)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3790. Min Act: -0.1700
Data Index: 1079250 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3947. Min Act: -0.1700
Data Index: 1471762 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3947. Min Act: -0.1700
Data Index: 1453844 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3947. Min Act: -0.1700
Data Index: 1578419 (Python Code)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3790. Min Act: -0.1700
Data Index: 1513239 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3947. Min Act: -0.1700
Data Index: 1112837 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3633. Min Act: -0.1700
Data Index: 1634240 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7079. Min Range: -3.7079
Max Act: 3.3476. Min Act: -0.1700
Data Index: 1424216 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19