Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 114 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.8431. Min Act: -0.1700
Data Index: 959364 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.7806. Min Act: -0.1700
Data Index: 100718 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.7181. Min Act: -0.1700
Data Index: 1215742 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.6556. Min Act: -0.1700
Data Index: 658905 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5306. Min Act: -0.1700
Data Index: 805384 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5619. Min Act: -0.1700
Data Index: 603186 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5306. Min Act: -0.1700
Data Index: 193574 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5306. Min Act: -0.1700
Data Index: 223723 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5306. Min Act: -0.1700
Data Index: 456580 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4994. Min Act: -0.1700
Data Index: 566386 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.5306. Min Act: -0.1700
Data Index: 1051021 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4994. Min Act: -0.1700
Data Index: 588795 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4994. Min Act: -0.1700
Data Index: 449064 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4056. Min Act: -0.1700
Data Index: 477877 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4681. Min Act: -0.1700
Data Index: 321946 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4681. Min Act: -0.1700
Data Index: 429347 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4681. Min Act: -0.1700
Data Index: 1297145 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4994. Min Act: -0.1700
Data Index: 933288 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4681. Min Act: -0.1700
Data Index: 1300847 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8431. Min Range: -4.8431
Max Act: 4.4369. Min Act: -0.1700
Data Index: 965394 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19