Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2035 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.5912. Min Act: -0.1700
Data Index: 531803 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.4037. Min Act: -0.1700
Data Index: 1212900 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.3412. Min Act: -0.1700
Data Index: 139017 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.2787. Min Act: -0.1700
Data Index: 50718 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.0912. Min Act: -0.1700
Data Index: 1062745 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.1850. Min Act: -0.1700
Data Index: 528395 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.1537. Min Act: -0.1700
Data Index: 1313100 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.2475. Min Act: -0.1700
Data Index: 313831 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.1225. Min Act: -0.1700
Data Index: 486704 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.0287. Min Act: -0.1700
Data Index: 968371 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.1225. Min Act: -0.1700
Data Index: 564397 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.0912. Min Act: -0.1700
Data Index: 384391 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.9975. Min Act: -0.1700
Data Index: 1278716 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.9037. Min Act: -0.1700
Data Index: 153508 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.9662. Min Act: -0.1700
Data Index: 931853 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.9350. Min Act: -0.1700
Data Index: 1327847 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.0600. Min Act: -0.1700
Data Index: 592129 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.9037. Min Act: -0.1700
Data Index: 718366 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5912. Min Range: -6.5912
Max Act: 6.0287. Min Act: -0.1700
Data Index: 1060397 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5912. Min Range: -6.5912
Max Act: 5.8725. Min Act: -0.1700
Data Index: 499190 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19