Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 430 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0474. Min Act: -0.0003
Data Index: 1148749 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0401. Min Act: -0.0002
Data Index: 920466 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0369. Min Act: -0.0002
Data Index: 863453 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0376. Min Act: -0.0002
Data Index: 347145 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0356. Min Act: -0.0002
Data Index: 1519320 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0291. Min Act: -0.0003
Data Index: 303593 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0312. Min Act: -0.0002
Data Index: 208841 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0260. Min Act: -0.0003
Data Index: 1940220 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0262. Min Act: -0.0003
Data Index: 1171325 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0258. Min Act: -0.0003
Data Index: 791482 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0263. Min Act: -0.0003
Data Index: 894081 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0268. Min Act: -0.0003
Data Index: 63435 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0268. Min Act: -0.0003
Data Index: 832329 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0266. Min Act: -0.0003
Data Index: 282085 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0266. Min Act: -0.0003
Data Index: 454337 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0266. Min Act: -0.0003
Data Index: 617335 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0243. Min Act: -0.0003
Data Index: 946090 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0243. Min Act: -0.0003
Data Index: 1044767 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0243. Min Act: -0.0003
Data Index: 1378001 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0474. Min Range: -0.0474
Max Act: 0.0243. Min Act: -0.0003
Data Index: 1408881 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19