Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1914 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0367. Min Range: -4.0367
Max Act: 4.0367. Min Act: -0.1700
Data Index: 868791 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.9429. Min Act: -0.1700
Data Index: 1358108 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1021662 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8803. Min Act: -0.1700
Data Index: 708065 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8491. Min Act: -0.1700
Data Index: 374588 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8178. Min Act: -0.1700
Data Index: 137283 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8803. Min Act: -0.1700
Data Index: 1134703 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8491. Min Act: -0.1700
Data Index: 157746 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8178. Min Act: -0.1700
Data Index: 33457 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.8803. Min Act: -0.1700
Data Index: 267459 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7552. Min Act: -0.1700
Data Index: 997175 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7552. Min Act: -0.1700
Data Index: 381177 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7552. Min Act: -0.1700
Data Index: 683590 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7239. Min Act: -0.1700
Data Index: 366269 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7865. Min Act: -0.1700
Data Index: 187026 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7552. Min Act: -0.1700
Data Index: 4904 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7552. Min Act: -0.1700
Data Index: 1115248 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.6926. Min Act: -0.1700
Data Index: 760109 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7239. Min Act: -0.1700
Data Index: 835562 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0367. Min Range: -4.0367
Max Act: 3.7239. Min Act: -0.1700
Data Index: 1000815 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19