Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 106 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6971. Min Act: -0.1700
Data Index: 745146 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6651. Min Act: -0.1700
Data Index: 1348236 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6490. Min Act: -0.1700
Data Index: 1359833 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6330. Min Act: -0.1700
Data Index: 316443 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6008. Min Act: -0.1700
Data Index: 668665 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6008. Min Act: -0.1700
Data Index: 352021 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6008. Min Act: -0.1700
Data Index: 107592 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.6008. Min Act: -0.1700
Data Index: 629684 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5847. Min Act: -0.1700
Data Index: 600993 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5847. Min Act: -0.1700
Data Index: 1242000 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 257314 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 750271 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 940238 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 869476 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 404457 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 72182 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5363. Min Act: -0.1700
Data Index: 380866 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5686. Min Act: -0.1700
Data Index: 1291412 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 887575 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6971. Min Range: -2.6971
Max Act: 2.5525. Min Act: -0.1700
Data Index: 936203 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19