Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1878 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.5025. Min Act: -0.1700
Data Index: 504576 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.4701. Min Act: -0.1700
Data Index: 1643567 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.4376. Min Act: -0.1700
Data Index: 976995 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.4213. Min Act: -0.1700
Data Index: 312939 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3560. Min Act: -0.1700
Data Index: 554193 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3724. Min Act: -0.1700
Data Index: 1490084 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3560. Min Act: -0.1700
Data Index: 1507304 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3232. Min Act: -0.1700
Data Index: 89921 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3232. Min Act: -0.1700
Data Index: 1643457 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3068. Min Act: -0.1700
Data Index: 1456107 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.3068. Min Act: -0.1700
Data Index: 162528 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2904. Min Act: -0.1700
Data Index: 1594853 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2739. Min Act: -0.1700
Data Index: 1524357 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2739. Min Act: -0.1700
Data Index: 1362783 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2739. Min Act: -0.1700
Data Index: 1443407 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2904. Min Act: -0.1700
Data Index: 1410026 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2574. Min Act: -0.1700
Data Index: 1568928 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2574. Min Act: -0.1700
Data Index: 320610 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2409. Min Act: -0.1700
Data Index: 843661 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5025. Min Range: -2.5025
Max Act: 2.2574. Min Act: -0.1700
Data Index: 942353 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19