Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2021 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0270. Min Range: -4.0270
Max Act: 4.0270. Min Act: -0.1699
Data Index: 871382 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9645. Min Act: -0.1700
Data Index: 694813 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9645. Min Act: -0.1700
Data Index: 1239060 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 1322197 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 748918 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9645. Min Act: -0.1700
Data Index: 730077 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 1306560 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 180398 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 845917 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 959744 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9332. Min Act: -0.1700
Data Index: 1190694 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9020. Min Act: -0.1700
Data Index: 311228 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.9020. Min Act: -0.1700
Data Index: 1184745 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 48768 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 100855 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 582713 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 73419 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 953929 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8707. Min Act: -0.1700
Data Index: 837162 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0270. Min Range: -4.0270
Max Act: 3.8394. Min Act: -0.1700
Data Index: 1030122 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19