Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 147 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1472. Min Range: -3.1472
Max Act: 3.1472. Min Act: -0.1700
Data Index: 1413596 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1472. Min Range: -3.1472
Max Act: 3.0210. Min Act: -0.1700
Data Index: 1527995 (Python Code)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1472. Min Range: -3.1472
Max Act: 3.0210. Min Act: -0.1700
Data Index: 748531 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.9736. Min Act: -0.1700
Data Index: 1083755 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.9261. Min Act: -0.1700
Data Index: 1408545 (Python Code)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.9261. Min Act: -0.1700
Data Index: 603687 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8785. Min Act: -0.1700
Data Index: 1211713 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8944. Min Act: -0.1700
Data Index: 387058 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8785. Min Act: -0.1700
Data Index: 1531650 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8944. Min Act: -0.1700
Data Index: 1612446 (Python Code)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8467. Min Act: -0.1700
Data Index: 173748 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.9261. Min Act: -0.1700
Data Index: 422011 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8626. Min Act: -0.1700
Data Index: 1412845 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8467. Min Act: -0.1700
Data Index: 1457045 (Python Code)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8308. Min Act: -0.1700
Data Index: 1590370 (Python Code)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8626. Min Act: -0.1700
Data Index: 1514051 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8149. Min Act: -0.1700
Data Index: 698943 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.8149. Min Act: -0.1700
Data Index: 1561589 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.7990. Min Act: -0.1700
Data Index: 1418369 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1472. Min Range: -3.1472
Max Act: 2.7831. Min Act: -0.1700
Data Index: 185063 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19