Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 974 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.5896. Min Act: -0.1700
Data Index: 100197 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.5896. Min Act: -0.1700
Data Index: 609799 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.5583. Min Act: -0.1700
Data Index: 1165510 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.5583. Min Act: -0.1700
Data Index: 176934 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.5271. Min Act: -0.1700
Data Index: 897996 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4645. Min Act: -0.1700
Data Index: 740501 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4645. Min Act: -0.1700
Data Index: 871869 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4645. Min Act: -0.1700
Data Index: 774396 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3708. Min Act: -0.1700
Data Index: 407171 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4645. Min Act: -0.1700
Data Index: 608077 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4333. Min Act: -0.1700
Data Index: 736465 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.4020. Min Act: -0.1700
Data Index: 915173 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3708. Min Act: -0.1700
Data Index: 1313306 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.2770. Min Act: -0.1700
Data Index: 249078 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3395. Min Act: -0.1700
Data Index: 60301 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3395. Min Act: -0.1700
Data Index: 83407 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3395. Min Act: -0.1700
Data Index: 240029 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.2145. Min Act: -0.1700
Data Index: 298995 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.2770. Min Act: -0.1700
Data Index: 282106 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5896. Min Range: -4.5896
Max Act: 4.3083. Min Act: -0.1700
Data Index: 395042 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19