Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1805 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7776. Min Act: -0.1700
Data Index: 374147 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7617. Min Act: -0.1700
Data Index: 473326 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7457. Min Act: -0.1700
Data Index: 891504 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6978. Min Act: -0.1700
Data Index: 1400469 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7138. Min Act: -0.1700
Data Index: 1135119 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7138. Min Act: -0.1700
Data Index: 892282 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6817. Min Act: -0.1700
Data Index: 920828 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6817. Min Act: -0.1700
Data Index: 1303216 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.7138. Min Act: -0.1700
Data Index: 1066070 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6657. Min Act: -0.1700
Data Index: 1586027 (Python Code)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6978. Min Act: -0.1700
Data Index: 841896 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6657. Min Act: -0.1700
Data Index: 542642 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6497. Min Act: -0.1700
Data Index: 1420810 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6657. Min Act: -0.1700
Data Index: 1422430 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6657. Min Act: -0.1700
Data Index: 1399779 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6176. Min Act: -0.1700
Data Index: 804654 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6176. Min Act: -0.1700
Data Index: 347598 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6336. Min Act: -0.1700
Data Index: 596662 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6817. Min Act: -0.1700
Data Index: 1119327 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7776. Min Range: -2.7776
Max Act: 2.6336. Min Act: -0.1700
Data Index: 1596288 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19