Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2724 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.4626. Min Act: -0.0001
Data Index: 129309 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.5125. Min Act: -0.0001
Data Index: 160473 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.4139. Min Act: -0.0001
Data Index: 1067412 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.4239. Min Act: -0.0001
Data Index: 508561 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.4065. Min Act: -0.0001
Data Index: 911556 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3587. Min Act: -0.0001
Data Index: 816231 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3582. Min Act: -0.0001
Data Index: 1272236 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3650. Min Act: -0.0001
Data Index: 452440 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3068. Min Act: -0.0001
Data Index: 1214394 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3510. Min Act: -0.0001
Data Index: 1072433 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3319. Min Act: -0.0001
Data Index: 298808 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3518. Min Act: -0.0001
Data Index: 1455595 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3489. Min Act: -0.0001
Data Index: 1490724 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.2710. Min Act: -0.0001
Data Index: 752162 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3100. Min Act: -0.0001
Data Index: 222565 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3416. Min Act: -0.0001
Data Index: 1508915 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3552. Min Act: -0.0001
Data Index: 961053 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3400. Min Act: -0.0001
Data Index: 195943 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3241. Min Act: -0.0001
Data Index: 592850 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5125. Min Range: -0.5125
Max Act: 0.3235. Min Act: -0.0001
Data Index: 1630941 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19