Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1873 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.4447. Min Act: -0.1700
Data Index: 1141905 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.4284. Min Act: -0.1700
Data Index: 1314202 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3632. Min Act: -0.1700
Data Index: 400871 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3468. Min Act: -0.1700
Data Index: 725923 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 831697 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 999330 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 568316 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 20852 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3140. Min Act: -0.1700
Data Index: 922371 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 469659 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3304. Min Act: -0.1700
Data Index: 1242102 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2975. Min Act: -0.1700
Data Index: 1301559 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3140. Min Act: -0.1700
Data Index: 205702 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2975. Min Act: -0.1700
Data Index: 783259 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2975. Min Act: -0.1700
Data Index: 514088 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.3140. Min Act: -0.1700
Data Index: 1132958 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2811. Min Act: -0.1700
Data Index: 579322 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2975. Min Act: -0.1700
Data Index: 1254934 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2646. Min Act: -0.1700
Data Index: 362819 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4447. Min Range: -2.4447
Max Act: 2.2811. Min Act: -0.1700
Data Index: 915045 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19