Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3255 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.8192. Min Act: -0.0001
Data Index: 1459110 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.9461. Min Act: -0.0001
Data Index: 1648192 (Python Code)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.4466. Min Act: -0.0001
Data Index: 1530880 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.7927. Min Act: -0.0001
Data Index: 1483652 (Python Code)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.7307. Min Act: -0.0001
Data Index: 1507602 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.3158. Min Act: -0.0001
Data Index: 1400788 (Python Code)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.5694. Min Act: -0.0001
Data Index: 1486085 (Python Code)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.4710. Min Act: -0.0001
Data Index: 1530512 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.4483. Min Act: -0.0001
Data Index: 1516331 (Python Code)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.2810. Min Act: -0.0001
Data Index: 1618863 (Python Code)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.3286. Min Act: -0.0001
Data Index: 1586882 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.2162. Min Act: -0.0001
Data Index: 1604743 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.3016. Min Act: -0.0001
Data Index: 1518437 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.3150. Min Act: -0.0001
Data Index: 1630354 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.4333. Min Act: -0.0001
Data Index: 1651666 (Python Code)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.0425. Min Act: -0.0001
Data Index: 1389558 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.2665. Min Act: -0.0001
Data Index: 1478444 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.3495. Min Act: -0.0001
Data Index: 1637188 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.4585. Min Act: -0.0001
Data Index: 1383445 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9461. Min Range: -2.9461
Max Act: 2.1110. Min Act: -0.0001
Data Index: 1566644 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19