Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2285 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.9754. Min Act: -0.0002
Data Index: 562692 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.7104. Min Act: -0.0002
Data Index: 606928 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.7575. Min Act: -0.0002
Data Index: 758664 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.7535. Min Act: -0.0002
Data Index: 552304 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.6490. Min Act: -0.0002
Data Index: 1327512 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.4026. Min Act: -0.0002
Data Index: 2451 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.5468. Min Act: -0.0002
Data Index: 963032 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.3612. Min Act: -0.0002
Data Index: 832829 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.3320. Min Act: -0.0002
Data Index: 751010 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.4417. Min Act: -0.0002
Data Index: 229135 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.2455. Min Act: -0.0002
Data Index: 388687 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.3291. Min Act: -0.0002
Data Index: 210058 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.2405. Min Act: -0.0002
Data Index: 31119 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.1338. Min Act: -0.0002
Data Index: 1287008 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.2123. Min Act: -0.0002
Data Index: 372536 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.1825. Min Act: -0.0002
Data Index: 71965 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.2268. Min Act: -0.0002
Data Index: 52424 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.1115. Min Act: -0.0002
Data Index: 1040188 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.1686. Min Act: -0.0002
Data Index: 317960 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.9754. Min Range: -2.9754
Max Act: 2.0117. Min Act: -0.0002
Data Index: 1347322 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full textTruncated
Full Text #19