Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 463 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.8058. Min Act: -0.1700
Data Index: 603052 (C4 (Web Text))
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.8058. Min Act: -0.1700
Data Index: 288659 (C4 (Web Text))
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.7261. Min Act: -0.1700
Data Index: 501142 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.7261. Min Act: -0.1700
Data Index: 781244 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.7101. Min Act: -0.1700
Data Index: 850025 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6941. Min Act: -0.1700
Data Index: 860399 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.7101. Min Act: -0.1700
Data Index: 1248475 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.7101. Min Act: -0.1700
Data Index: 1311467 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6941. Min Act: -0.1700
Data Index: 1588336 (Python Code)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6941. Min Act: -0.1700
Data Index: 1239939 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6941. Min Act: -0.1700
Data Index: 591126 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6941. Min Act: -0.1700
Data Index: 543230 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6781. Min Act: -0.1700
Data Index: 125923 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6781. Min Act: -0.1700
Data Index: 36249 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6781. Min Act: -0.1700
Data Index: 20009 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6781. Min Act: -0.1700
Data Index: 122130 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6781. Min Act: -0.1700
Data Index: 683927 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6621. Min Act: -0.1700
Data Index: 120257 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6460. Min Act: -0.1700
Data Index: 268665 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8058. Min Range: -2.8058
Max Act: 2.6460. Min Act: -0.1700
Data Index: 265472 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19