Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 768 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.2448. Min Range: -5.2448
Max Act: 5.2448. Min Act: -0.1700
Data Index: 10363 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2448. Min Range: -5.2448
Max Act: 5.0261. Min Act: -0.1700
Data Index: 1352496 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.9011. Min Act: -0.1700
Data Index: 1054847 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.9323. Min Act: -0.1700
Data Index: 227518 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.8698. Min Act: -0.1700
Data Index: 1024519 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7448. Min Act: -0.1700
Data Index: 1250839 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.8386. Min Act: -0.1700
Data Index: 416732 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7761. Min Act: -0.1700
Data Index: 163501 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7448. Min Act: -0.1700
Data Index: 153788 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6823. Min Act: -0.1700
Data Index: 383479 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7135. Min Act: -0.1700
Data Index: 627607 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7135. Min Act: -0.1700
Data Index: 1006005 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6823. Min Act: -0.1700
Data Index: 1299287 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6510. Min Act: -0.1700
Data Index: 319693 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.5885. Min Act: -0.1700
Data Index: 1322736 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6823. Min Act: -0.1700
Data Index: 531384 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6823. Min Act: -0.1700
Data Index: 1003887 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.7135. Min Act: -0.1700
Data Index: 758440 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6198. Min Act: -0.1700
Data Index: 1047531 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2448. Min Range: -5.2448
Max Act: 4.6198. Min Act: -0.1700
Data Index: 540180 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19