Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2015 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.3884. Min Act: -0.1699
Data Index: 1459841 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.3259. Min Act: -0.1698
Data Index: 232962 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.3259. Min Act: -0.1700
Data Index: 541049 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.2634. Min Act: -0.1698
Data Index: 59324 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.2634. Min Act: -0.1700
Data Index: 8059 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.2321. Min Act: -0.1700
Data Index: 1345757 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.2009. Min Act: -0.1700
Data Index: 1009023 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1696. Min Act: -0.1699
Data Index: 794286 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1696. Min Act: -0.1700
Data Index: 1091238 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1384. Min Act: -0.1700
Data Index: 68841 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1566830 (Python Code)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1384. Min Act: -0.1699
Data Index: 155914 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1384. Min Act: -0.1700
Data Index: 1206887 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1071. Min Act: -0.1700
Data Index: 373665 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.0446. Min Act: -0.1699
Data Index: 820034 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1254552 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.0759. Min Act: -0.1700
Data Index: 576657 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1014827 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.0134. Min Act: -0.1700
Data Index: 2263 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3884. Min Range: -6.3884
Max Act: 6.1071. Min Act: -0.1700
Data Index: 1129156 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19