Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 269 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.6735. Min Act: -0.1700
Data Index: 723173 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.4860. Min Act: -0.1700
Data Index: 23463 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.4234. Min Act: -0.1700
Data Index: 301178 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.4860. Min Act: -0.1700
Data Index: 1152383 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3922. Min Act: -0.1700
Data Index: 452406 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1184809 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.4234. Min Act: -0.1700
Data Index: 1045487 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3609. Min Act: -0.1700
Data Index: 118220 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3609. Min Act: -0.1700
Data Index: 296403 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3922. Min Act: -0.1700
Data Index: 233522 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3922. Min Act: -0.1700
Data Index: 603124 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3922. Min Act: -0.1700
Data Index: 1169597 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3297. Min Act: -0.1700
Data Index: 247600 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3297. Min Act: -0.1700
Data Index: 981016 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3297. Min Act: -0.1700
Data Index: 933476 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3297. Min Act: -0.1700
Data Index: 1259125 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1247197 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.3609. Min Act: -0.1700
Data Index: 716697 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.2984. Min Act: -0.1700
Data Index: 160965 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6735. Min Range: -4.6735
Max Act: 4.2984. Min Act: -0.1700
Data Index: 234644 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19