Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 771 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.5078. Min Act: -0.1700
Data Index: 382665 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4753. Min Act: -0.1700
Data Index: 3292 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4916. Min Act: -0.1700
Data Index: 1382974 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4591. Min Act: -0.1700
Data Index: 513941 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 401075 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 552652 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 1457168 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 1285928 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 1014600 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 383840 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4266. Min Act: -0.1700
Data Index: 1636487 (Python Code)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4266. Min Act: -0.1700
Data Index: 1550053 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4429. Min Act: -0.1700
Data Index: 1422675 (Python Code)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 572662 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4266. Min Act: -0.1700
Data Index: 140505 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 1275478 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 1471677 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 1550954 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 1628241 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5078. Min Range: -2.5078
Max Act: 2.4103. Min Act: -0.1700
Data Index: 1466344 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19