Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 20 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.4522. Min Act: -0.1700
Data Index: 1121351 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.4522. Min Act: -0.1700
Data Index: 37827 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3897. Min Act: -0.1700
Data Index: 328330 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3897. Min Act: -0.1700
Data Index: 546765 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.4210. Min Act: -0.1700
Data Index: 735793 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.4210. Min Act: -0.1700
Data Index: 339416 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3897. Min Act: -0.1700
Data Index: 71742 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3897. Min Act: -0.1700
Data Index: 73298 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 593570 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 1068017 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 621337 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 450149 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 742458 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.2960. Min Act: -0.1700
Data Index: 1222940 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3585. Min Act: -0.1700
Data Index: 157950 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 883436 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.3272. Min Act: -0.1700
Data Index: 745116 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.2647. Min Act: -0.1700
Data Index: 576129 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.2960. Min Act: -0.1700
Data Index: 753936 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4522. Min Range: -4.4522
Max Act: 4.2960. Min Act: -0.1700
Data Index: 770947 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19