Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1926 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.2545. Min Act: -0.1700
Data Index: 162004 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.1920. Min Act: -0.1700
Data Index: 544402 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.1607. Min Act: -0.1700
Data Index: 1032617 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.1607. Min Act: -0.1700
Data Index: 1146693 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0982. Min Act: -0.1700
Data Index: 214812 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0982. Min Act: -0.1700
Data Index: 145464 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0982. Min Act: -0.1700
Data Index: 305822 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 177838 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0356. Min Act: -0.1700
Data Index: 921841 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 373497 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 88444 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 456878 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0356. Min Act: -0.1700
Data Index: 522350 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 560163 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0982. Min Act: -0.1700
Data Index: 223152 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 210162 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0669. Min Act: -0.1700
Data Index: 697338 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0356. Min Act: -0.1700
Data Index: 134267 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0356. Min Act: -0.1700
Data Index: 1237343 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2545. Min Range: -4.2545
Max Act: 4.0356. Min Act: -0.1700
Data Index: 628765 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19