Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 619 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.0829. Min Range: -5.0829
Max Act: 5.0829. Min Act: -0.1700
Data Index: 910359 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0829. Min Range: -5.0829
Max Act: 5.0829. Min Act: -0.1700
Data Index: 381641 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0829. Min Range: -5.0829
Max Act: 5.0204. Min Act: -0.1700
Data Index: 1031125 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.9579. Min Act: -0.1700
Data Index: 128530 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.9579. Min Act: -0.1700
Data Index: 1170803 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.9266. Min Act: -0.1700
Data Index: 3828 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8954. Min Act: -0.1700
Data Index: 1266706 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1342148 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1026258 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8641. Min Act: -0.1700
Data Index: 1149510 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 833863 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 985234 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 1238457 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 1275167 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8016. Min Act: -0.1700
Data Index: 422402 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 98983 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8329. Min Act: -0.1700
Data Index: 994965 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8016. Min Act: -0.1700
Data Index: 1164963 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8016. Min Act: -0.1700
Data Index: 132000 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0829. Min Range: -5.0829
Max Act: 4.8016. Min Act: -0.1700
Data Index: 584744 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19