Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1877 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.1117. Min Act: -0.1700
Data Index: 1311772 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0802. Min Act: -0.1700
Data Index: 786692 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0802. Min Act: -0.1700
Data Index: 1341628 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0644. Min Act: -0.1700
Data Index: 606252 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0486. Min Act: -0.1700
Data Index: 280315 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0329. Min Act: -0.1700
Data Index: 1024919 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0171. Min Act: -0.1700
Data Index: 225644 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0012. Min Act: -0.1700
Data Index: 416060 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0171. Min Act: -0.1700
Data Index: 115061 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0171. Min Act: -0.1700
Data Index: 1200815 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0012. Min Act: -0.1700
Data Index: 693801 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0012. Min Act: -0.1700
Data Index: 1170216 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0012. Min Act: -0.1700
Data Index: 166824 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1117. Min Range: -3.1117
Max Act: 3.0012. Min Act: -0.1700
Data Index: 453573 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9854. Min Act: -0.1700
Data Index: 835835 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9854. Min Act: -0.1700
Data Index: 1182671 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9854. Min Act: -0.1700
Data Index: 616565 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9696. Min Act: -0.1700
Data Index: 523460 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9696. Min Act: -0.1700
Data Index: 1136231 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1117. Min Range: -3.1117
Max Act: 2.9854. Min Act: -0.1700
Data Index: 1141117 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19