Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 500 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.7341. Min Act: -0.1700
Data Index: 156444 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.7341. Min Act: -0.1700
Data Index: 386544 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.7021. Min Act: -0.1700
Data Index: 1292693 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.7021. Min Act: -0.1700
Data Index: 1181492 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.7181. Min Act: -0.1700
Data Index: 1111122 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6861. Min Act: -0.1700
Data Index: 49634 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 797360 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6861. Min Act: -0.1700
Data Index: 626210 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 1234924 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6861. Min Act: -0.1700
Data Index: 842140 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 944185 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 971403 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6861. Min Act: -0.1700
Data Index: 300644 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6861. Min Act: -0.1700
Data Index: 379677 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6541. Min Act: -0.1700
Data Index: 158864 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 285101 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6541. Min Act: -0.1700
Data Index: 944991 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 192803 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 536943 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7341. Min Range: -2.7341
Max Act: 2.6701. Min Act: -0.1700
Data Index: 580874 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19