Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 198 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4855. Min Act: -0.1700
Data Index: 77561 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4855. Min Act: -0.1700
Data Index: 1324388 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4855. Min Act: -0.1700
Data Index: 33407 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4855. Min Act: -0.1700
Data Index: 855512 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4229. Min Act: -0.1700
Data Index: 72706 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.3917. Min Act: -0.1700
Data Index: 708862 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4229. Min Act: -0.1700
Data Index: 475239 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.3292. Min Act: -0.1700
Data Index: 297318 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.3917. Min Act: -0.1700
Data Index: 1231217 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.3604. Min Act: -0.1700
Data Index: 692698 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.4855. Min Act: -0.1700
Data Index: 27643 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.3292. Min Act: -0.1700
Data Index: 345416 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2979. Min Act: -0.1700
Data Index: 708885 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2667. Min Act: -0.1700
Data Index: 572775 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2979. Min Act: -0.1700
Data Index: 7860 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2354. Min Act: -0.1700
Data Index: 88112 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2354. Min Act: -0.1700
Data Index: 681753 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2042. Min Act: -0.1700
Data Index: 1068539 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2667. Min Act: -0.1700
Data Index: 1072705 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4855. Min Range: -4.4855
Max Act: 4.2042. Min Act: -0.1700
Data Index: 1007470 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19