Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 178 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.5729. Min Act: -0.1700
Data Index: 91530 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.5083. Min Act: -0.1700
Data Index: 1003221 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.4759. Min Act: -0.1700
Data Index: 1191203 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.4271. Min Act: -0.1700
Data Index: 1358526 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3945. Min Act: -0.1700
Data Index: 884160 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.4109. Min Act: -0.1700
Data Index: 531264 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3782. Min Act: -0.1700
Data Index: 1048791 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.4109. Min Act: -0.1700
Data Index: 850259 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3782. Min Act: -0.1700
Data Index: 45301 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3945. Min Act: -0.1700
Data Index: 529098 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3945. Min Act: -0.1700
Data Index: 595988 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3455. Min Act: -0.1700
Data Index: 918532 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3619. Min Act: -0.1700
Data Index: 624964 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3619. Min Act: -0.1700
Data Index: 852954 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3455. Min Act: -0.1700
Data Index: 1277103 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3619. Min Act: -0.1700
Data Index: 696649 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3782. Min Act: -0.1700
Data Index: 919113 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3782. Min Act: -0.1700
Data Index: 960808 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3619. Min Act: -0.1700
Data Index: 1020481 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5729. Min Range: -2.5729
Max Act: 2.3455. Min Act: -0.1700
Data Index: 1381556 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19