Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 494 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.8082. Min Act: -0.1700
Data Index: 1648167 (Python Code)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1646297 (Python Code)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1390018 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.7144. Min Act: -0.1700
Data Index: 582339 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.7144. Min Act: -0.1700
Data Index: 1112329 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1401141 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1217182 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6832. Min Act: -0.1700
Data Index: 1350804 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6519. Min Act: -0.1700
Data Index: 714909 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 8667 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 1369806 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 1426575 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 6101 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 1300939 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.5582. Min Act: -0.1700
Data Index: 177020 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.5269. Min Act: -0.1700
Data Index: 755841 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.6207. Min Act: -0.1700
Data Index: 575800 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.5582. Min Act: -0.1700
Data Index: 1586737 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.5582. Min Act: -0.1700
Data Index: 1442273 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8082. Min Range: -4.8082
Max Act: 4.4644. Min Act: -0.1700
Data Index: 1535475 (Python Code)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19