Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 224 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.7494. Min Act: -0.0001
Data Index: 734100 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.7203. Min Act: -0.0001
Data Index: 775407 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.6560. Min Act: -0.0001
Data Index: 849576 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.4287. Min Act: -0.0001
Data Index: 706782 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.5268. Min Act: -0.0001
Data Index: 915879 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.4972. Min Act: -0.0001
Data Index: 812283 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1939. Min Act: -0.0001
Data Index: 839985 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.4904. Min Act: -0.0001
Data Index: 458423 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.3674. Min Act: -0.0001
Data Index: 421921 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.2213. Min Act: -0.0001
Data Index: 913838 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1544. Min Act: -0.0001
Data Index: 528875 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1918. Min Act: -0.0001
Data Index: 405252 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.3720. Min Act: -0.0001
Data Index: 541025 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1745. Min Act: -0.0001
Data Index: 193509 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.2942. Min Act: -0.0001
Data Index: 1146884 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1059. Min Act: -0.0001
Data Index: 506793 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1969. Min Act: -0.0001
Data Index: 457250 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1459. Min Act: -0.0001
Data Index: 913646 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1543. Min Act: -0.0001
Data Index: 372462 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7494. Min Range: -2.7494
Max Act: 2.1887. Min Act: -0.0001
Data Index: 264972 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19