Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.8278. Min Act: -0.1700
Data Index: 858987 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7966. Min Act: -0.1700
Data Index: 291759 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7966. Min Act: -0.1700
Data Index: 1165853 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7653. Min Act: -0.1700
Data Index: 1018429 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7653. Min Act: -0.1700
Data Index: 188379 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7653. Min Act: -0.1700
Data Index: 1124430 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7027. Min Act: -0.1700
Data Index: 1064128 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7340. Min Act: -0.1700
Data Index: 1192185 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7340. Min Act: -0.1700
Data Index: 1285896 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7027. Min Act: -0.1700
Data Index: 422848 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7027. Min Act: -0.1700
Data Index: 314422 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7340. Min Act: -0.1700
Data Index: 1104411 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7027. Min Act: -0.1700
Data Index: 814285 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.7027. Min Act: -0.1700
Data Index: 482557 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6714. Min Act: -0.1700
Data Index: 1107890 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6714. Min Act: -0.1700
Data Index: 541790 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6401. Min Act: -0.1700
Data Index: 1090545 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6401. Min Act: -0.1700
Data Index: 1159364 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6714. Min Act: -0.1700
Data Index: 513762 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8278. Min Range: -3.8278
Max Act: 3.6714. Min Act: -0.1700
Data Index: 1154522 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19