Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 84 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.7461. Min Act: -0.1700
Data Index: 1012490 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.6523. Min Act: -0.1700
Data Index: 85927 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.7461. Min Act: -0.1700
Data Index: 167739 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4961. Min Act: -0.1700
Data Index: 175445 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5586. Min Act: -0.1700
Data Index: 1039080 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4961. Min Act: -0.1700
Data Index: 1308238 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.6211. Min Act: -0.1700
Data Index: 410681 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5586. Min Act: -0.1700
Data Index: 806222 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5898. Min Act: -0.1700
Data Index: 616859 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5898. Min Act: -0.1700
Data Index: 602690 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5898. Min Act: -0.1700
Data Index: 310917 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5273. Min Act: -0.1700
Data Index: 554645 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4961. Min Act: -0.1700
Data Index: 396312 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5273. Min Act: -0.1700
Data Index: 102071 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5273. Min Act: -0.1700
Data Index: 174607 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4648. Min Act: -0.1700
Data Index: 160516 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5273. Min Act: -0.1700
Data Index: 684253 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.5586. Min Act: -0.1700
Data Index: 961077 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4648. Min Act: -0.1700
Data Index: 899588 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7461. Min Range: -4.7461
Max Act: 4.4648. Min Act: -0.1700
Data Index: 585658 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19