Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1771 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.4408. Min Range: -5.4408
Max Act: 5.4408. Min Act: -0.1700
Data Index: 299902 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4408. Min Range: -5.4408
Max Act: 5.2220. Min Act: -0.1700
Data Index: 136597 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9720. Min Act: -0.1699
Data Index: 908246 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9720. Min Act: -0.1700
Data Index: 806688 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9720. Min Act: -0.1700
Data Index: 824512 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9095. Min Act: -0.1700
Data Index: 75063 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9095. Min Act: -0.1700
Data Index: 634847 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8783. Min Act: -0.1700
Data Index: 501923 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8470. Min Act: -0.1700
Data Index: 957347 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8470. Min Act: -0.1700
Data Index: 1202434 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8158. Min Act: -0.1700
Data Index: 1052714 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8783. Min Act: -0.1700
Data Index: 1035447 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8783. Min Act: -0.1700
Data Index: 227004 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8783. Min Act: -0.1700
Data Index: 120071 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8470. Min Act: -0.1700
Data Index: 980248 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8470. Min Act: -0.1700
Data Index: 1020448 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8158. Min Act: -0.1700
Data Index: 529864 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.9095. Min Act: -0.1700
Data Index: 669115 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8470. Min Act: -0.1700
Data Index: 1183924 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4408. Min Range: -5.4408
Max Act: 4.8158. Min Act: -0.1700
Data Index: 71754 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19