Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3354 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.6280. Min Act: -0.0001
Data Index: 279656 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.7802. Min Act: -0.0001
Data Index: 707121 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.3410. Min Act: -0.0001
Data Index: 1147820 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.4368. Min Act: -0.0001
Data Index: 236521 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.2402. Min Act: -0.0001
Data Index: 133609 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.3337. Min Act: -0.0001
Data Index: 1105642 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.2712. Min Act: -0.0001
Data Index: 1130860 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.3803. Min Act: -0.0001
Data Index: 1212857 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1372. Min Act: -0.0001
Data Index: 852467 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.2504. Min Act: -0.0001
Data Index: 641165 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.0092. Min Act: -0.0001
Data Index: 1263787 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.2392. Min Act: -0.0001
Data Index: 1235102 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.0956. Min Act: -0.0001
Data Index: 707330 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1918. Min Act: -0.0001
Data Index: 1041924 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1385. Min Act: -0.0001
Data Index: 235428 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1413. Min Act: -0.0001
Data Index: 1141775 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1431. Min Act: -0.0001
Data Index: 1143511 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1248. Min Act: -0.0001
Data Index: 541242 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.2466. Min Act: -0.0001
Data Index: 874006 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7802. Min Range: -2.7802
Max Act: 2.1289. Min Act: -0.0001
Data Index: 818073 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19