Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3924 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.7875. Min Act: -0.0001
Data Index: 572518 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.6083. Min Act: -0.0001
Data Index: 701255 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.5985. Min Act: -0.0001
Data Index: 833778 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.6668. Min Act: -0.0001
Data Index: 644390 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.6266. Min Act: -0.0001
Data Index: 812491 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.5965. Min Act: -0.0001
Data Index: 753917 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4758. Min Act: -0.0001
Data Index: 1307639 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4489. Min Act: -0.0001
Data Index: 871930 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4818. Min Act: -0.0001
Data Index: 1325034 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4405. Min Act: -0.0001
Data Index: 151703 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4960. Min Act: -0.0001
Data Index: 61972 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4481. Min Act: -0.0001
Data Index: 1634636 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.3510. Min Act: -0.0001
Data Index: 1306910 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.3334. Min Act: -0.0001
Data Index: 319002 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4106. Min Act: -0.0001
Data Index: 1434898 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.3218. Min Act: -0.0001
Data Index: 669614 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.2624. Min Act: -0.0001
Data Index: 485330 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.4265. Min Act: -0.0001
Data Index: 1060821 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.3549. Min Act: -0.0001
Data Index: 1355498 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7875. Min Range: -1.7875
Max Act: 1.3045. Min Act: -0.0001
Data Index: 1394497 (Python Code)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19