Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2054 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.9411. Min Act: -0.0001
Data Index: 180404 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.9476. Min Act: -0.0001
Data Index: 195684 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.8089. Min Act: -0.0001
Data Index: 1213452 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7831. Min Act: -0.0001
Data Index: 1244094 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7409. Min Act: -0.0001
Data Index: 1189453 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7849. Min Act: -0.0001
Data Index: 682251 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7761. Min Act: -0.0001
Data Index: 37583 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7479. Min Act: -0.0001
Data Index: 717705 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.6977. Min Act: -0.0001
Data Index: 803482 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7331. Min Act: -0.0001
Data Index: 865597 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7385. Min Act: -0.0001
Data Index: 400292 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7243. Min Act: -0.0001
Data Index: 1098353 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7276. Min Act: -0.0001
Data Index: 916000 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7218. Min Act: -0.0001
Data Index: 1326080 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7470. Min Act: -0.0001
Data Index: 96851 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.6507. Min Act: -0.0001
Data Index: 698168 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7064. Min Act: -0.0001
Data Index: 533683 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7085. Min Act: -0.0001
Data Index: 1222609 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.7033. Min Act: -0.0001
Data Index: 260978 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9476. Min Range: -0.9476
Max Act: 0.6961. Min Act: -0.0001
Data Index: 305654 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19