Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6910. Min Act: -0.1700
Data Index: 1463073 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6750. Min Act: -0.1700
Data Index: 300365 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6910. Min Act: -0.1700
Data Index: 1405536 (Python Code)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6268. Min Act: -0.1700
Data Index: 861891 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6750. Min Act: -0.1700
Data Index: 1493533 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5947. Min Act: -0.1700
Data Index: 1367161 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5947. Min Act: -0.1700
Data Index: 1351225 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5463. Min Act: -0.1700
Data Index: 624827 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5624. Min Act: -0.1700
Data Index: 211352 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5463. Min Act: -0.1700
Data Index: 1608252 (Python Code)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5786. Min Act: -0.1700
Data Index: 920757 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5786. Min Act: -0.1700
Data Index: 520690 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.6107. Min Act: -0.1700
Data Index: 609615 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5624. Min Act: -0.1700
Data Index: 1397660 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5463. Min Act: -0.1700
Data Index: 181326 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5624. Min Act: -0.1700
Data Index: 1491896 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5140. Min Act: -0.1700
Data Index: 1151810 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5301. Min Act: -0.1700
Data Index: 772197 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.5301. Min Act: -0.1700
Data Index: 1269550 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6910. Min Range: -2.6910
Max Act: 2.4978. Min Act: -0.1700
Data Index: 1434833 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19