Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1585 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.6159. Min Act: -0.0001
Data Index: 997244 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.6328. Min Act: -0.0001
Data Index: 850054 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5689. Min Act: -0.0001
Data Index: 328199 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.6233. Min Act: -0.0001
Data Index: 940568 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5729. Min Act: -0.0001
Data Index: 1314654 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5828. Min Act: -0.0001
Data Index: 1408305 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5630. Min Act: -0.0001
Data Index: 989067 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5719. Min Act: -0.0001
Data Index: 1046772 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5529. Min Act: -0.0001
Data Index: 542833 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5521. Min Act: -0.0001
Data Index: 883669 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5410. Min Act: -0.0001
Data Index: 1148467 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5060. Min Act: -0.0001
Data Index: 823044 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5559. Min Act: -0.0001
Data Index: 229138 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5314. Min Act: -0.0001
Data Index: 180765 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5253. Min Act: -0.0001
Data Index: 936462 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5074. Min Act: -0.0001
Data Index: 1574903 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5069. Min Act: -0.0001
Data Index: 1264322 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5041. Min Act: -0.0001
Data Index: 389693 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5085. Min Act: -0.0001
Data Index: 642209 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6328. Min Range: -0.6328
Max Act: 0.5494. Min Act: -0.0001
Data Index: 787593 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19