Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1917 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.2314. Min Act: -0.1700
Data Index: 293859 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.1685. Min Act: -0.1700
Data Index: 122810 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.1212. Min Act: -0.1700
Data Index: 1446011 (Python Code)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.1212. Min Act: -0.1700
Data Index: 1405986 (Python Code)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0739. Min Act: -0.1700
Data Index: 1461338 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0581. Min Act: -0.1700
Data Index: 1436807 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0739. Min Act: -0.1700
Data Index: 1469779 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0897. Min Act: -0.1700
Data Index: 928263 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0739. Min Act: -0.1700
Data Index: 197592 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0581. Min Act: -0.1700
Data Index: 1378313 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0423. Min Act: -0.1700
Data Index: 315481 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0423. Min Act: -0.1700
Data Index: 1573128 (Python Code)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0581. Min Act: -0.1700
Data Index: 300870 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0581. Min Act: -0.1700
Data Index: 998387 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0423. Min Act: -0.1700
Data Index: 762637 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0266. Min Act: -0.1700
Data Index: 869733 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0108. Min Act: -0.1700
Data Index: 882618 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0266. Min Act: -0.1700
Data Index: 930448 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2314. Min Range: -3.2314
Max Act: 2.9949. Min Act: -0.1700
Data Index: 157714 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2314. Min Range: -3.2314
Max Act: 3.0108. Min Act: -0.1700
Data Index: 86668 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19