Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3267 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.8596. Min Act: -0.0001
Data Index: 183709 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.8174. Min Act: -0.0001
Data Index: 1021421 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.6940. Min Act: -0.0001
Data Index: 323065 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.7861. Min Act: -0.0001
Data Index: 603328 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5133. Min Act: -0.0001
Data Index: 759272 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.4977. Min Act: -0.0001
Data Index: 805084 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5669. Min Act: -0.0001
Data Index: 1253943 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.7086. Min Act: -0.0001
Data Index: 17657 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5843. Min Act: -0.0001
Data Index: 1087016 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5943. Min Act: -0.0001
Data Index: 155218 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5271. Min Act: -0.0001
Data Index: 1649756 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.4839. Min Act: -0.0001
Data Index: 735773 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5601. Min Act: -0.0001
Data Index: 1141583 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5601. Min Act: -0.0001
Data Index: 93043 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5602. Min Act: -0.0001
Data Index: 424489 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.6017. Min Act: -0.0001
Data Index: 1155775 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.5559. Min Act: -0.0001
Data Index: 1594307 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.3997. Min Act: -0.0001
Data Index: 1161581 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.4304. Min Act: -0.0001
Data Index: 429746 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8596. Min Range: -1.8596
Max Act: 1.3461. Min Act: -0.0001
Data Index: 735727 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19