Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1831 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.7168. Min Act: -0.1700
Data Index: 1296849 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.6231. Min Act: -0.1700
Data Index: 679928 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.5293. Min Act: -0.1700
Data Index: 1044723 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4981. Min Act: -0.1700
Data Index: 590214 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4668. Min Act: -0.1700
Data Index: 1325467 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4981. Min Act: -0.1700
Data Index: 404622 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4668. Min Act: -0.1700
Data Index: 522138 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4668. Min Act: -0.1700
Data Index: 312938 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 1002080 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 1077180 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4668. Min Act: -0.1700
Data Index: 535955 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 597058 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 183941 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 75422 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4043. Min Act: -0.1700
Data Index: 755022 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4043. Min Act: -0.1700
Data Index: 799827 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.3731. Min Act: -0.1700
Data Index: 434715 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4043. Min Act: -0.1700
Data Index: 686981 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4043. Min Act: -0.1700
Data Index: 385682 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7168. Min Range: -4.7168
Max Act: 4.4356. Min Act: -0.1700
Data Index: 1133706 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19