Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 396 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.2512. Min Act: -0.1700
Data Index: 837971 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.2512. Min Act: -0.1700
Data Index: 46467 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.1574. Min Act: -0.1700
Data Index: 801414 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.1574. Min Act: -0.1700
Data Index: 740204 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.1574. Min Act: -0.1700
Data Index: 1161207 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.1262. Min Act: -0.1700
Data Index: 842727 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0949. Min Act: -0.1700
Data Index: 515286 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0324. Min Act: -0.1700
Data Index: 1339182 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.1262. Min Act: -0.1700
Data Index: 1226976 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0324. Min Act: -0.1700
Data Index: 662576 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0637. Min Act: -0.1700
Data Index: 950724 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0637. Min Act: -0.1700
Data Index: 506911 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0324. Min Act: -0.1700
Data Index: 166387 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0011. Min Act: -0.1700
Data Index: 1230569 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0324. Min Act: -0.1700
Data Index: 874494 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0011. Min Act: -0.1700
Data Index: 1225228 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2512. Min Range: -4.2512
Max Act: 4.0011. Min Act: -0.1700
Data Index: 915488 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2512. Min Range: -4.2512
Max Act: 3.9386. Min Act: -0.1700
Data Index: 240081 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2512. Min Range: -4.2512
Max Act: 3.9699. Min Act: -0.1700
Data Index: 951458 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2512. Min Range: -4.2512
Max Act: 3.9699. Min Act: -0.1700
Data Index: 1171957 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19