Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1510 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.9814. Min Act: -0.1700
Data Index: 791622 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.8564. Min Act: -0.1700
Data Index: 1193598 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.8877. Min Act: -0.1700
Data Index: 981898 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7939. Min Act: -0.1700
Data Index: 1121179 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.8252. Min Act: -0.1700
Data Index: 1042718 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7314. Min Act: -0.1700
Data Index: 277547 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7627. Min Act: -0.1700
Data Index: 394302 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7627. Min Act: -0.1700
Data Index: 230665 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.6689. Min Act: -0.1700
Data Index: 1157426 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7627. Min Act: -0.1700
Data Index: 450896 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7939. Min Act: -0.1700
Data Index: 393285 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7002. Min Act: -0.1700
Data Index: 1243358 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7314. Min Act: -0.1700
Data Index: 302823 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.6689. Min Act: -0.1700
Data Index: 781017 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7314. Min Act: -0.1700
Data Index: 649180 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7002. Min Act: -0.1700
Data Index: 156341 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7627. Min Act: -0.1700
Data Index: 1275519 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.7627. Min Act: -0.1700
Data Index: 420965 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.6689. Min Act: -0.1700
Data Index: 814031 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9814. Min Range: -4.9814
Max Act: 4.6377. Min Act: -0.1700
Data Index: 844688 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19