Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2305 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4582. Min Range: -2.4582
Max Act: 2.4582. Min Act: -0.0001
Data Index: 458439 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4582. Min Range: -2.4582
Max Act: 2.2706. Min Act: -0.0001
Data Index: 999383 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.9104. Min Act: -0.0001
Data Index: 302480 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.7048. Min Act: -0.0001
Data Index: 1022933 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.6920. Min Act: -0.0001
Data Index: 1351091 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.6280. Min Act: -0.0001
Data Index: 602782 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5098. Min Act: -0.0001
Data Index: 503438 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5982. Min Act: -0.0001
Data Index: 790983 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5143. Min Act: -0.0001
Data Index: 205140 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5980. Min Act: -0.0001
Data Index: 440636 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5632. Min Act: -0.0001
Data Index: 368487 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.6185. Min Act: -0.0001
Data Index: 1034351 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5171. Min Act: -0.0002
Data Index: 407570 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5107. Min Act: -0.0001
Data Index: 566728 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5965. Min Act: -0.0001
Data Index: 192812 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5335. Min Act: -0.0001
Data Index: 964993 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.4874. Min Act: -0.0001
Data Index: 401993 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5290. Min Act: -0.0001
Data Index: 516841 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5171. Min Act: -0.0001
Data Index: 995410 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4582. Min Range: -2.4582
Max Act: 1.5130. Min Act: -0.0001
Data Index: 604010 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19