Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 896 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.4423. Min Act: -0.1700
Data Index: 1113440 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3953. Min Act: -0.1700
Data Index: 994773 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3953. Min Act: -0.1700
Data Index: 646175 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3796. Min Act: -0.1700
Data Index: 228452 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3639. Min Act: -0.1700
Data Index: 554710 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3796. Min Act: -0.1700
Data Index: 975069 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3953. Min Act: -0.1700
Data Index: 876203 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3796. Min Act: -0.1700
Data Index: 688619 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3796. Min Act: -0.1700
Data Index: 547738 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3639. Min Act: -0.1700
Data Index: 1109714 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3639. Min Act: -0.1700
Data Index: 640608 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3639. Min Act: -0.1700
Data Index: 773791 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3325. Min Act: -0.1700
Data Index: 369560 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3482. Min Act: -0.1700
Data Index: 1013411 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3482. Min Act: -0.1700
Data Index: 618504 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3482. Min Act: -0.1700
Data Index: 643196 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3325. Min Act: -0.1700
Data Index: 869765 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3482. Min Act: -0.1700
Data Index: 1290998 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3325. Min Act: -0.1700
Data Index: 489797 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4423. Min Range: -3.4423
Max Act: 3.3168. Min Act: -0.1700
Data Index: 68741 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19