Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1993 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.2046. Min Act: -0.1700
Data Index: 830162 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.1733. Min Act: -0.1700
Data Index: 366056 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.1421. Min Act: -0.1700
Data Index: 845865 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.1108. Min Act: -0.1700
Data Index: 561467 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.1733. Min Act: -0.1700
Data Index: 719244 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.0483. Min Act: -0.1700
Data Index: 498346 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.0170. Min Act: -0.1700
Data Index: 797632 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.0170. Min Act: -0.1700
Data Index: 524939 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2046. Min Range: -4.2046
Max Act: 4.0483. Min Act: -0.1700
Data Index: 946588 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9858. Min Act: -0.1700
Data Index: 785442 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9858. Min Act: -0.1700
Data Index: 104142 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9858. Min Act: -0.1700
Data Index: 248407 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.8919. Min Act: -0.1700
Data Index: 187947 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9545. Min Act: -0.1700
Data Index: 700431 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9232. Min Act: -0.1700
Data Index: 733005 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9232. Min Act: -0.1700
Data Index: 353795 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.8919. Min Act: -0.1700
Data Index: 1132598 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9232. Min Act: -0.1700
Data Index: 835025 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9232. Min Act: -0.1700
Data Index: 293346 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2046. Min Range: -4.2046
Max Act: 3.9232. Min Act: -0.1700
Data Index: 397163 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19