Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.6947. Min Act: -0.0001
Data Index: 802957 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.6091. Min Act: -0.0001
Data Index: 1155480 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.6424. Min Act: -0.0001
Data Index: 364253 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5873. Min Act: -0.0001
Data Index: 517440 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5773. Min Act: -0.0001
Data Index: 310776 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5422. Min Act: -0.0001
Data Index: 1566116 (Python Code)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5585. Min Act: -0.0001
Data Index: 925326 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5670. Min Act: -0.0001
Data Index: 716851 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5819. Min Act: -0.0001
Data Index: 874977 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5489. Min Act: -0.0001
Data Index: 244879 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5778. Min Act: -0.0001
Data Index: 1044867 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5413. Min Act: -0.0001
Data Index: 182655 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5728. Min Act: -0.0001
Data Index: 738664 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5874. Min Act: -0.0001
Data Index: 1556087 (Python Code)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5172. Min Act: -0.0001
Data Index: 298571 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5466. Min Act: -0.0001
Data Index: 545775 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5653. Min Act: -0.0001
Data Index: 390561 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5084. Min Act: -0.0001
Data Index: 589209 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5605. Min Act: -0.0001
Data Index: 471122 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6947. Min Range: -0.6947
Max Act: 0.5272. Min Act: -0.0001
Data Index: 142772 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19