Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2121. Min Range: -5.2121
Max Act: 5.1808. Min Act: -0.1700
Data Index: 1093949 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2121. Min Range: -5.2121
Max Act: 5.2121. Min Act: -0.1700
Data Index: 391366 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2121. Min Range: -5.2121
Max Act: 5.0871. Min Act: -0.1700
Data Index: 262421 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.9933. Min Act: -0.1700
Data Index: 1205201 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.9933. Min Act: -0.1700
Data Index: 536937 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.9933. Min Act: -0.1700
Data Index: 78316 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.9308. Min Act: -0.1700
Data Index: 736791 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.9308. Min Act: -0.1700
Data Index: 783779 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.8058. Min Act: -0.1700
Data Index: 758804 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.8683. Min Act: -0.1700
Data Index: 973790 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 563454 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.8371. Min Act: -0.1700
Data Index: 960065 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 742582 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.8371. Min Act: -0.1700
Data Index: 362892 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.8371. Min Act: -0.1700
Data Index: 593338 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 779712 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 1204415 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 802211 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 727840 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2121. Min Range: -5.2121
Max Act: 4.7746. Min Act: -0.1700
Data Index: 186208 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19