Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 45 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.4057. Min Act: -0.1700
Data Index: 207723 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.3744. Min Act: -0.1700
Data Index: 944049 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.4057. Min Act: -0.1700
Data Index: 549538 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.2494. Min Act: -0.1700
Data Index: 1262228 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.0932. Min Act: -0.1700
Data Index: 611 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9994. Min Act: -0.1700
Data Index: 198994 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.1244. Min Act: -0.1700
Data Index: 1073871 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9682. Min Act: -0.1700
Data Index: 302812 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.0619. Min Act: -0.1700
Data Index: 244342 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.0307. Min Act: -0.1700
Data Index: 434718 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4057. Min Range: -5.4057
Max Act: 5.0619. Min Act: -0.1700
Data Index: 745488 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9994. Min Act: -0.1700
Data Index: 987071 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9682. Min Act: -0.1700
Data Index: 121687 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9682. Min Act: -0.1700
Data Index: 1356076 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9682. Min Act: -0.1700
Data Index: 600797 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9057. Min Act: -0.1700
Data Index: 798586 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9057. Min Act: -0.1700
Data Index: 1111569 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9682. Min Act: -0.1700
Data Index: 957323 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.9057. Min Act: -0.1700
Data Index: 446639 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4057. Min Range: -5.4057
Max Act: 4.8744. Min Act: -0.1700
Data Index: 602692 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19