Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 42 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.3501. Min Act: -0.1700
Data Index: 975556 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.1142. Min Act: -0.1700
Data Index: 460258 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.0195. Min Act: -0.1700
Data Index: 918484 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.0827. Min Act: -0.1700
Data Index: 1645537 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.0353. Min Act: -0.1700
Data Index: 1031106 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.0511. Min Act: -0.1700
Data Index: 269927 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9879. Min Act: -0.1700
Data Index: 360446 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3501. Min Range: -3.3501
Max Act: 3.0195. Min Act: -0.1700
Data Index: 1303462 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9246. Min Act: -0.1700
Data Index: 24462 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9246. Min Act: -0.1700
Data Index: 454073 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9246. Min Act: -0.1700
Data Index: 1360368 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9087. Min Act: -0.1700
Data Index: 1192715 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.8929. Min Act: -0.1700
Data Index: 404988 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9404. Min Act: -0.1700
Data Index: 382940 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9563. Min Act: -0.1700
Data Index: 1336374 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9246. Min Act: -0.1700
Data Index: 53193 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.8929. Min Act: -0.1700
Data Index: 962264 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1122485 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.8770. Min Act: -0.1700
Data Index: 1238887 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3501. Min Range: -3.3501
Max Act: 2.9087. Min Act: -0.1700
Data Index: 1113100 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19