Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 113 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.7815. Min Act: -0.1700
Data Index: 351247 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.3127. Min Act: -0.1700
Data Index: 956503 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.3439. Min Act: -0.1700
Data Index: 324494 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.2189. Min Act: -0.1700
Data Index: 939247 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.1877. Min Act: -0.1700
Data Index: 555263 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.1251. Min Act: -0.1700
Data Index: 1144834 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.1251. Min Act: -0.1700
Data Index: 813541 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.1251. Min Act: -0.1700
Data Index: 619676 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0939. Min Act: -0.1700
Data Index: 432454 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.1251. Min Act: -0.1700
Data Index: 173580 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0939. Min Act: -0.1700
Data Index: 837940 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0939. Min Act: -0.1700
Data Index: 724949 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0626. Min Act: -0.1700
Data Index: 1155541 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0939. Min Act: -0.1700
Data Index: 435384 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0626. Min Act: -0.1700
Data Index: 426876 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0626. Min Act: -0.1700
Data Index: 931244 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0001. Min Act: -0.1700
Data Index: 918054 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0314. Min Act: -0.1700
Data Index: 494281 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0314. Min Act: -0.1700
Data Index: 957014 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7815. Min Range: -4.7815
Max Act: 4.0314. Min Act: -0.1700
Data Index: 110587 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19