Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 39 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0572. Min Range: -4.0572
Max Act: 4.0572. Min Act: -0.1700
Data Index: 120821 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9947. Min Act: -0.1700
Data Index: 1176828 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0572. Min Range: -4.0572
Max Act: 4.0259. Min Act: -0.1700
Data Index: 378241 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9947. Min Act: -0.1700
Data Index: 328018 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 596309 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9634. Min Act: -0.1700
Data Index: 51078 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9947. Min Act: -0.1700
Data Index: 1214808 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0572. Min Range: -4.0572
Max Act: 4.0259. Min Act: -0.1700
Data Index: 1298992 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 240299 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9947. Min Act: -0.1700
Data Index: 1152298 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9634. Min Act: -0.1700
Data Index: 662515 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9634. Min Act: -0.1700
Data Index: 177946 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9634. Min Act: -0.1700
Data Index: 1033217 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 224174 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 877563 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 142170 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 734330 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9321. Min Act: -0.1700
Data Index: 842111 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9634. Min Act: -0.1700
Data Index: 75550 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0572. Min Range: -4.0572
Max Act: 3.9009. Min Act: -0.1700
Data Index: 923229 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19