Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2761 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1847. Min Range: -3.1847
Max Act: 3.1847. Min Act: -0.0001
Data Index: 260734 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.8624. Min Act: -0.0001
Data Index: 937139 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.6840. Min Act: -0.0001
Data Index: 783996 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.6340. Min Act: -0.0001
Data Index: 509399 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.6465. Min Act: -0.0001
Data Index: 306484 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.4950. Min Act: -0.0001
Data Index: 425462 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.4353. Min Act: -0.0001
Data Index: 100176 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.5545. Min Act: -0.0001
Data Index: 1224605 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.4195. Min Act: -0.0001
Data Index: 502902 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.4661. Min Act: -0.0001
Data Index: 905527 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.3450. Min Act: -0.0001
Data Index: 1144858 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.2781. Min Act: -0.0001
Data Index: 353470 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.2554. Min Act: -0.0001
Data Index: 692140 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.2784. Min Act: -0.0001
Data Index: 826756 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.3614. Min Act: -0.0001
Data Index: 161966 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.1181. Min Act: -0.0001
Data Index: 366616 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.3097. Min Act: -0.0001
Data Index: 1073895 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.1610. Min Act: -0.0001
Data Index: 1250773 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.2566. Min Act: -0.0001
Data Index: 202026 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1847. Min Range: -3.1847
Max Act: 2.0939. Min Act: -0.0001
Data Index: 59575 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19