Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3880 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.9122. Min Act: -0.0001
Data Index: 1428040 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.5498. Min Act: -0.0001
Data Index: 1417433 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.5190. Min Act: -0.0001
Data Index: 1421996 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.5477. Min Act: -0.0001
Data Index: 1626774 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.4950. Min Act: -0.0001
Data Index: 1631157 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.4169. Min Act: -0.0001
Data Index: 1554911 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.4654. Min Act: -0.0001
Data Index: 1452783 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3682. Min Act: -0.0001
Data Index: 1503003 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3241. Min Act: -0.0001
Data Index: 1434117 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.2689. Min Act: -0.0001
Data Index: 1584368 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3103. Min Act: -0.0001
Data Index: 1464459 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.2994. Min Act: -0.0001
Data Index: 1645503 (Python Code)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.2477. Min Act: -0.0001
Data Index: 1490192 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.2902. Min Act: -0.0001
Data Index: 1486940 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3272. Min Act: -0.0001
Data Index: 1555043 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3171. Min Act: -0.0001
Data Index: 1419943 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3091. Min Act: -0.0001
Data Index: 1415503 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.2745. Min Act: -0.0001
Data Index: 1425322 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.5020. Min Act: -0.0001
Data Index: 1366769 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9122. Min Range: -1.9122
Max Act: 1.3276. Min Act: -0.0001
Data Index: 1377184 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19