Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3625 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.4665. Min Act: -0.0001
Data Index: 546557 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.1703. Min Act: -0.0001
Data Index: 666463 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3925. Min Act: -0.0001
Data Index: 1003174 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2776. Min Act: -0.0001
Data Index: 549802 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.4163. Min Act: -0.0001
Data Index: 367979 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3414. Min Act: -0.0001
Data Index: 807930 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2347. Min Act: -0.0001
Data Index: 1341690 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2445. Min Act: -0.0001
Data Index: 495384 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3816. Min Act: -0.0001
Data Index: 501852 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3064. Min Act: -0.0001
Data Index: 142256 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2955. Min Act: -0.0001
Data Index: 970632 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.4141. Min Act: -0.0001
Data Index: 1161998 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2218. Min Act: -0.0001
Data Index: 42323 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3450. Min Act: -0.0001
Data Index: 1303518 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.4855. Min Act: -0.0001
Data Index: 559166 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.4086. Min Act: -0.0001
Data Index: 1240567 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.3013. Min Act: -0.0001
Data Index: 1118292 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.0691. Min Act: -0.0001
Data Index: 1341993 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.1956. Min Act: -0.0001
Data Index: 1141101 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4855. Min Range: -1.4855
Max Act: 1.2453. Min Act: -0.0001
Data Index: 1308668 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19