Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 792 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0339. Min Act: -0.1700
Data Index: 819893 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0339. Min Act: -0.1700
Data Index: 80791 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0026. Min Act: -0.1700
Data Index: 1305776 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0026. Min Act: -0.1700
Data Index: 703787 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0026. Min Act: -0.1700
Data Index: 1130933 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9401. Min Act: -0.1700
Data Index: 1019577 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 345920 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1003647 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9401. Min Act: -0.1700
Data Index: 963512 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 290512 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1347984 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8775. Min Act: -0.1700
Data Index: 9248 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 150726 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8462. Min Act: -0.1700
Data Index: 490142 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1212499 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8462. Min Act: -0.1700
Data Index: 1297228 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8775. Min Act: -0.1700
Data Index: 270086 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8462. Min Act: -0.1700
Data Index: 57755 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8462. Min Act: -0.1700
Data Index: 132267 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9088. Min Act: -0.1700
Data Index: 987144 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19