Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 994 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.3707. Min Act: -0.1700
Data Index: 577450 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.3216. Min Act: -0.1700
Data Index: 1264321 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2887. Min Act: -0.1700
Data Index: 1551756 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2887. Min Act: -0.1700
Data Index: 138645 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2392. Min Act: -0.1700
Data Index: 786382 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2722. Min Act: -0.1700
Data Index: 1456637 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2557. Min Act: -0.1700
Data Index: 240138 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2392. Min Act: -0.1700
Data Index: 44966 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2392. Min Act: -0.1700
Data Index: 1389340 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 354038 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2061. Min Act: -0.1700
Data Index: 169071 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 1370137 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 1373042 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 1457096 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2061. Min Act: -0.1700
Data Index: 1379062 (Python Code)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 1477960 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2227. Min Act: -0.1700
Data Index: 1507363 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2392. Min Act: -0.1700
Data Index: 1462070 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2061. Min Act: -0.1700
Data Index: 1436325 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3707. Min Range: -2.3707
Max Act: 2.2061. Min Act: -0.1700
Data Index: 1547491 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19