Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 303 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7850. Min Act: -0.1700
Data Index: 213874 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7850. Min Act: -0.1700
Data Index: 666692 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7531. Min Act: -0.1700
Data Index: 967607 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7531. Min Act: -0.1700
Data Index: 40880 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7371. Min Act: -0.1700
Data Index: 1137183 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7371. Min Act: -0.1700
Data Index: 976350 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7371. Min Act: -0.1700
Data Index: 592582 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 1265565 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 1108573 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 938329 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 463958 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 1093425 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7052. Min Act: -0.1700
Data Index: 1073536 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 842158 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 427225 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 398021 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 184957 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 849445 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 209055 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7850. Min Range: -2.7850
Max Act: 2.7211. Min Act: -0.1700
Data Index: 398309 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19