Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3903 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.8423. Min Act: -0.0001
Data Index: 518582 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.9945. Min Act: -0.0001
Data Index: 1174811 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.4129. Min Act: -0.0001
Data Index: 151599 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.3745. Min Act: -0.0001
Data Index: 974280 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.3615. Min Act: -0.0001
Data Index: 233148 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.4299. Min Act: -0.0001
Data Index: 457160 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.3388. Min Act: -0.0001
Data Index: 197450 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9945. Min Range: -2.9945
Max Act: 2.2235. Min Act: -0.0001
Data Index: 341620 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.9933. Min Act: -0.0001
Data Index: 18715 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.7486. Min Act: -0.0001
Data Index: 806534 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.4119. Min Act: -0.0001
Data Index: 474606 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.3968. Min Act: -0.0001
Data Index: 38921 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.5083. Min Act: -0.0001
Data Index: 881458 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.0646. Min Act: -0.0000
Data Index: 151931 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9945. Min Range: -2.9945
Max Act: 1.0247. Min Act: -0.0001
Data Index: 888786 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9945. Min Range: -2.9945
Max Act: 0.9308. Min Act: -0.0001
Data Index: 588539 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9945. Min Range: -2.9945
Max Act: 0.8122. Min Act: -0.0000
Data Index: 1193712 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9945. Min Range: -2.9945
Max Act: 0.8362. Min Act: -0.0000
Data Index: 1572602 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9945. Min Range: -2.9945
Max Act: 0.8143. Min Act: -0.0000
Data Index: 1417392 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9945. Min Range: -2.9945
Max Act: 0.8171. Min Act: 0.0001
Data Index: 18337 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19