Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2022 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.9516. Min Act: -0.1700
Data Index: 480548 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.8723. Min Act: -0.1700
Data Index: 465886 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7769. Min Act: -0.1700
Data Index: 765289 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7769. Min Act: -0.1700
Data Index: 182767 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7609. Min Act: -0.1700
Data Index: 1229578 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7450. Min Act: -0.1700
Data Index: 1050536 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7769. Min Act: -0.1700
Data Index: 855636 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7450. Min Act: -0.1700
Data Index: 1130364 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7450. Min Act: -0.1700
Data Index: 490431 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 921908 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7130. Min Act: -0.1700
Data Index: 1027176 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.7130. Min Act: -0.1700
Data Index: 189582 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 440645 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 797012 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 1295044 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6810. Min Act: -0.1700
Data Index: 892049 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 426020 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6810. Min Act: -0.1700
Data Index: 936865 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6810. Min Act: -0.1700
Data Index: 1224172 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9516. Min Range: -2.9516
Max Act: 2.6970. Min Act: -0.1700
Data Index: 502678 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19