Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4073 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.3139. Min Act: -0.0002
Data Index: 302791 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.1560. Min Act: -0.0001
Data Index: 606613 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0905. Min Act: -0.0002
Data Index: 287014 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0901. Min Act: -0.0001
Data Index: 725111 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.8784. Min Act: -0.0001
Data Index: 1159725 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.9152. Min Act: -0.0002
Data Index: 263631 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.8871. Min Act: -0.0001
Data Index: 850218 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0549. Min Act: -0.0002
Data Index: 479815 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0779. Min Act: -0.0001
Data Index: 584642 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.6618. Min Act: -0.0001
Data Index: 597899 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.8745. Min Act: -0.0001
Data Index: 1330221 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.8385. Min Act: -0.0002
Data Index: 489081 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.6710. Min Act: -0.0001
Data Index: 963948 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.9801. Min Act: -0.0002
Data Index: 165870 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0088. Min Act: -0.0001
Data Index: 454062 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3139. Min Range: -2.3139
Max Act: 2.0709. Min Act: -0.0001
Data Index: 1232074 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.7451. Min Act: -0.0002
Data Index: 152298 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.9023. Min Act: -0.0001
Data Index: 672450 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.9186. Min Act: -0.0002
Data Index: 627307 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3139. Min Range: -2.3139
Max Act: 1.8089. Min Act: -0.0001
Data Index: 318601 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19