Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2023 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.4221. Min Act: -0.1700
Data Index: 75861 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3895. Min Act: -0.1700
Data Index: 625539 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3895. Min Act: -0.1700
Data Index: 758489 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3731. Min Act: -0.1700
Data Index: 805473 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3568. Min Act: -0.1700
Data Index: 733447 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3731. Min Act: -0.1700
Data Index: 164604 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3240. Min Act: -0.1700
Data Index: 742082 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3076. Min Act: -0.1700
Data Index: 1480910 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3076. Min Act: -0.1700
Data Index: 63906 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 771639 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3240. Min Act: -0.1700
Data Index: 1030925 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 1315601 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 46897 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3076. Min Act: -0.1700
Data Index: 893532 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 682159 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.3076. Min Act: -0.1700
Data Index: 850175 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 329880 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2911. Min Act: -0.1700
Data Index: 584530 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2747. Min Act: -0.1700
Data Index: 565117 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4221. Min Range: -2.4221
Max Act: 2.2582. Min Act: -0.1700
Data Index: 1377299 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19