Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1307 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.9903. Min Act: -0.1700
Data Index: 280149 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.9587. Min Act: -0.1700
Data Index: 877591 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.9429. Min Act: -0.1700
Data Index: 394873 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.9112. Min Act: -0.1700
Data Index: 1195884 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.8636. Min Act: -0.1700
Data Index: 983697 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.8318. Min Act: -0.1700
Data Index: 193853 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.8318. Min Act: -0.1700
Data Index: 489130 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7999. Min Act: -0.1700
Data Index: 1291237 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7999. Min Act: -0.1700
Data Index: 375769 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7840. Min Act: -0.1700
Data Index: 1279368 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7840. Min Act: -0.1700
Data Index: 12152 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7681. Min Act: -0.1700
Data Index: 745522 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7521. Min Act: -0.1700
Data Index: 58215 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7361. Min Act: -0.1700
Data Index: 992209 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7521. Min Act: -0.1700
Data Index: 1269169 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7521. Min Act: -0.1700
Data Index: 621798 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7521. Min Act: -0.1700
Data Index: 1230705 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7361. Min Act: -0.1700
Data Index: 494826 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7361. Min Act: -0.1700
Data Index: 957019 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9903. Min Range: -2.9903
Max Act: 2.7361. Min Act: -0.1700
Data Index: 1290952 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19