Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2670 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.8932. Min Act: -0.0001
Data Index: 1000636 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.8103. Min Act: -0.0001
Data Index: 891537 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.7914. Min Act: -0.0001
Data Index: 1199517 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.5153. Min Act: -0.0001
Data Index: 156075 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.5881. Min Act: -0.0001
Data Index: 546910 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.6238. Min Act: -0.0001
Data Index: 1230712 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3920. Min Act: -0.0001
Data Index: 368763 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3269. Min Act: -0.0001
Data Index: 268391 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.2570. Min Act: -0.0001
Data Index: 351945 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3302. Min Act: -0.0001
Data Index: 42773 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3069. Min Act: -0.0001
Data Index: 885149 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3386. Min Act: -0.0001
Data Index: 375170 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.2946. Min Act: -0.0001
Data Index: 142202 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3413. Min Act: -0.0001
Data Index: 761699 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.2976. Min Act: -0.0001
Data Index: 148576 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.2450. Min Act: -0.0001
Data Index: 1025537 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3141. Min Act: -0.0001
Data Index: 422081 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3129. Min Act: -0.0001
Data Index: 1194465 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.2370. Min Act: -0.0001
Data Index: 832459 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8932. Min Range: -1.8932
Max Act: 1.3207. Min Act: -0.0001
Data Index: 5376 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19