Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9872. Min Act: -0.1700
Data Index: 504341 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9872. Min Act: -0.1700
Data Index: 672749 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9872. Min Act: -0.1700
Data Index: 1330135 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9398. Min Act: -0.1700
Data Index: 894199 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9398. Min Act: -0.1700
Data Index: 1334588 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9239. Min Act: -0.1700
Data Index: 1197376 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9239. Min Act: -0.1700
Data Index: 1205941 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.9081. Min Act: -0.1700
Data Index: 1115947 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8763. Min Act: -0.1700
Data Index: 1124049 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8605. Min Act: -0.1700
Data Index: 1073679 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8605. Min Act: -0.1700
Data Index: 921573 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8605. Min Act: -0.1700
Data Index: 1028341 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8605. Min Act: -0.1700
Data Index: 1016789 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8446. Min Act: -0.1700
Data Index: 771078 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8287. Min Act: -0.1700
Data Index: 608029 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.8127. Min Act: -0.1700
Data Index: 568224 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.7809. Min Act: -0.1700
Data Index: 596803 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.7968. Min Act: -0.1700
Data Index: 1129074 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.7809. Min Act: -0.1700
Data Index: 1313011 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9872. Min Range: -2.9872
Max Act: 2.7809. Min Act: -0.1700
Data Index: 860778 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19