Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3217 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5787. Min Act: -0.0001
Data Index: 828925 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5922. Min Act: -0.0002
Data Index: 218512 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5780. Min Act: -0.0001
Data Index: 250480 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5469. Min Act: -0.0001
Data Index: 959160 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5850. Min Act: -0.0001
Data Index: 950404 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4324. Min Act: -0.0001
Data Index: 155457 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5654. Min Act: -0.0001
Data Index: 526739 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.6048. Min Act: -0.0001
Data Index: 65104 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4469. Min Act: -0.0001
Data Index: 415280 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5788. Min Act: -0.0001
Data Index: 1310322 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5139. Min Act: -0.0001
Data Index: 1076647 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4874. Min Act: -0.0001
Data Index: 773734 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4722. Min Act: -0.0001
Data Index: 1127079 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4197. Min Act: -0.0001
Data Index: 561595 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4075. Min Act: -0.0001
Data Index: 293222 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4704. Min Act: -0.0001
Data Index: 658165 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4837. Min Act: -0.0001
Data Index: 357064 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.3928. Min Act: -0.0001
Data Index: 1329141 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.5172. Min Act: -0.0001
Data Index: 626004 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6048. Min Range: -1.6048
Max Act: 1.4665. Min Act: -0.0001
Data Index: 151384 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19