Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3483 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.4576. Min Act: -0.0001
Data Index: 534592 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3416. Min Act: -0.0001
Data Index: 405247 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3675. Min Act: -0.0001
Data Index: 873254 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3461. Min Act: -0.0001
Data Index: 238078 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.4462. Min Act: -0.0001
Data Index: 408223 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.4046. Min Act: -0.0001
Data Index: 1227315 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3435. Min Act: -0.0001
Data Index: 954051 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3749. Min Act: -0.0001
Data Index: 589024 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.2959. Min Act: -0.0001
Data Index: 126418 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3514. Min Act: -0.0001
Data Index: 454729 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.2437. Min Act: -0.0001
Data Index: 1355819 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3073. Min Act: -0.0001
Data Index: 570210 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.2142. Min Act: -0.0001
Data Index: 462409 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.2759. Min Act: -0.0001
Data Index: 720028 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.1968. Min Act: -0.0001
Data Index: 1065 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.2936. Min Act: -0.0001
Data Index: 479054 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.1986. Min Act: -0.0001
Data Index: 1081040 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.3371. Min Act: -0.0001
Data Index: 912217 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.0772. Min Act: -0.0001
Data Index: 573661 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4576. Min Range: -1.4576
Max Act: 1.1987. Min Act: -0.0001
Data Index: 608215 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19