Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 354 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.3163. Min Act: -0.0001
Data Index: 1000761 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.2973. Min Act: -0.0001
Data Index: 992931 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.2945. Min Act: -0.0001
Data Index: 782376 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.1545. Min Act: -0.0001
Data Index: 1575044 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.1072. Min Act: -0.0001
Data Index: 684136 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.1591. Min Act: -0.0001
Data Index: 88089 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.0544. Min Act: -0.0001
Data Index: 1165685 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.0146. Min Act: -0.0001
Data Index: 1007004 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9960. Min Act: -0.0001
Data Index: 882868 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9841. Min Act: -0.0001
Data Index: 1256507 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9188. Min Act: -0.0001
Data Index: 810640 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9121. Min Act: -0.0001
Data Index: 327726 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3163. Min Range: -2.3163
Max Act: 2.1190. Min Act: -0.0001
Data Index: 161541 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9000. Min Act: -0.0001
Data Index: 998752 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.8520. Min Act: -0.0001
Data Index: 177040 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9545. Min Act: -0.0001
Data Index: 1377871 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9416. Min Act: -0.0001
Data Index: 153187 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9210. Min Act: -0.0001
Data Index: 1113094 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9176. Min Act: -0.0001
Data Index: 920647 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3163. Min Range: -2.3163
Max Act: 1.9199. Min Act: -0.0001
Data Index: 480712 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19