Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2784 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.2505. Min Range: -3.2505
Max Act: 3.2505. Min Act: -0.0001
Data Index: 222477 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.8626. Min Act: -0.0001
Data Index: 846667 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.9726. Min Act: -0.0001
Data Index: 177880 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.7654. Min Act: -0.0001
Data Index: 168413 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.6846. Min Act: -0.0001
Data Index: 1181847 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.6749. Min Act: -0.0001
Data Index: 1330230 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.6527. Min Act: -0.0001
Data Index: 247217 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.3925. Min Act: -0.0001
Data Index: 1207973 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.6618. Min Act: -0.0001
Data Index: 777955 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.6326. Min Act: -0.0001
Data Index: 871764 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.2618. Min Act: -0.0001
Data Index: 428881 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.4543. Min Act: -0.0001
Data Index: 289706 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.5472. Min Act: -0.0001
Data Index: 221109 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.4205. Min Act: -0.0001
Data Index: 399447 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.3486. Min Act: -0.0001
Data Index: 57754 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.3368. Min Act: -0.0001
Data Index: 1091115 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.3467. Min Act: -0.0001
Data Index: 641888 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.1940. Min Act: -0.0001
Data Index: 398919 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.1795. Min Act: -0.0001
Data Index: 262385 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2505. Min Range: -3.2505
Max Act: 2.1978. Min Act: -0.0001
Data Index: 547664 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19