Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2015 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8727. Min Act: -0.1700
Data Index: 1513269 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8727. Min Act: -0.1700
Data Index: 1376826 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8409. Min Act: -0.1700
Data Index: 914779 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8409. Min Act: -0.1700
Data Index: 1461534 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8250. Min Act: -0.1700
Data Index: 1121785 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8250. Min Act: -0.1699
Data Index: 1546261 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8250. Min Act: -0.1700
Data Index: 1369881 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8409. Min Act: -0.1700
Data Index: 1559015 (Python Code)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8250. Min Act: -0.1700
Data Index: 1544613 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8091. Min Act: -0.1700
Data Index: 1631069 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1486753 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8091. Min Act: -0.1700
Data Index: 1365518 (Python Code)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8091. Min Act: -0.1700
Data Index: 1475280 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.8250. Min Act: -0.1700
Data Index: 591847 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1587670 (Python Code)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1460102 (Python Code)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1596991 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1611922 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1426832 (Python Code)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8727. Min Range: -2.8727
Max Act: 2.7932. Min Act: -0.1700
Data Index: 1638897 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19