Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1074 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2786. Min Act: -0.1700
Data Index: 63084 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2621. Min Act: -0.1700
Data Index: 1059288 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 1359304 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2621. Min Act: -0.1700
Data Index: 1006736 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 210562 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2291. Min Act: -0.1700
Data Index: 865266 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2621. Min Act: -0.1700
Data Index: 1224088 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 928118 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 529962 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 773723 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2456. Min Act: -0.1700
Data Index: 145874 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1228177 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2125. Min Act: -0.1700
Data Index: 69786 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1049843 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1053807 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2125. Min Act: -0.1700
Data Index: 1203385 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2125. Min Act: -0.1700
Data Index: 1322859 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2125. Min Act: -0.1700
Data Index: 746792 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.2291. Min Act: -0.1700
Data Index: 147239 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2786. Min Range: -2.2786
Max Act: 2.1959. Min Act: -0.1700
Data Index: 1112071 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19