Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 114 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5872. Min Act: -0.1700
Data Index: 784303 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5711. Min Act: -0.1700
Data Index: 515388 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5711. Min Act: -0.1700
Data Index: 610850 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5388. Min Act: -0.1700
Data Index: 1290784 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5065. Min Act: -0.1700
Data Index: 143583 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.5226. Min Act: -0.1700
Data Index: 936111 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 582047 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 1154355 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 899745 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 356407 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 630275 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 1291198 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 536505 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 1332116 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 294188 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 1322827 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 189950 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4740. Min Act: -0.1700
Data Index: 75434 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4578. Min Act: -0.1700
Data Index: 889256 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5872. Min Range: -2.5872
Max Act: 2.4416. Min Act: -0.1700
Data Index: 52374 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19