Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4402 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4169. Min Act: -0.0001
Data Index: 1505940 (Python Code)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4931. Min Act: -0.0001
Data Index: 1485491 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4736. Min Act: -0.0001
Data Index: 1464351 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.3486. Min Act: -0.0001
Data Index: 1366996 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.3489. Min Act: -0.0001
Data Index: 1617724 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2298. Min Act: -0.0001
Data Index: 1598501 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.0615. Min Act: -0.0001
Data Index: 1605738 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4136. Min Act: -0.0001
Data Index: 1367291 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2476. Min Act: -0.0001
Data Index: 1396050 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2595. Min Act: -0.0001
Data Index: 1488247 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2498. Min Act: -0.0001
Data Index: 1361771 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2397. Min Act: -0.0001
Data Index: 1431371 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.1416. Min Act: -0.0001
Data Index: 1545838 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.3615. Min Act: -0.0001
Data Index: 1641372 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2384. Min Act: -0.0001
Data Index: 1582947 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.2437. Min Act: -0.0001
Data Index: 1474000 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4849. Min Act: -0.0001
Data Index: 1392468 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.4811. Min Act: -0.0001
Data Index: 1456035 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.3475. Min Act: -0.0001
Data Index: 1611200 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4931. Min Range: -2.4931
Max Act: 2.0853. Min Act: -0.0001
Data Index: 1493488 (Python Code)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19