Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4055 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.6144. Min Act: -0.0001
Data Index: 44863 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.6033. Min Act: -0.0001
Data Index: 437793 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.5950. Min Act: -0.0000
Data Index: 980677 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.5588. Min Act: -0.0000
Data Index: 902572 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4872. Min Act: -0.0001
Data Index: 1328456 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.5344. Min Act: -0.0001
Data Index: 649273 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4187. Min Act: -0.0001
Data Index: 1155107 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.5835. Min Act: -0.0000
Data Index: 905051 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4881. Min Act: -0.0000
Data Index: 275077 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.2853. Min Act: -0.0001
Data Index: 546155 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4046. Min Act: -0.0001
Data Index: 1051768 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.5779. Min Act: -0.0000
Data Index: 683292 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4198. Min Act: -0.0000
Data Index: 446658 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.2770. Min Act: -0.0001
Data Index: 1008766 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4459. Min Act: -0.0001
Data Index: 334834 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4910. Min Act: -0.0001
Data Index: 55961 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.3687. Min Act: -0.0001
Data Index: 88494 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.1787. Min Act: -0.0001
Data Index: 888791 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.4136. Min Act: -0.0000
Data Index: 564575 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6144. Min Range: -2.6144
Max Act: 2.2933. Min Act: -0.0000
Data Index: 231388 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19