Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1905 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0808. Min Act: -0.1700
Data Index: 575684 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0651. Min Act: -0.1700
Data Index: 458015 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0335. Min Act: -0.1700
Data Index: 681212 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0177. Min Act: -0.1700
Data Index: 333417 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0335. Min Act: -0.1700
Data Index: 402714 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0019. Min Act: -0.1700
Data Index: 162021 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0808. Min Range: -3.0808
Max Act: 3.0019. Min Act: -0.1700
Data Index: 522219 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9861. Min Act: -0.1700
Data Index: 304409 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9702. Min Act: -0.1700
Data Index: 700920 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9861. Min Act: -0.1700
Data Index: 868180 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9861. Min Act: -0.1700
Data Index: 18888 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9544. Min Act: -0.1700
Data Index: 760868 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9861. Min Act: -0.1700
Data Index: 796902 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9544. Min Act: -0.1700
Data Index: 924236 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9386. Min Act: -0.1700
Data Index: 119399 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9702. Min Act: -0.1700
Data Index: 756006 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9386. Min Act: -0.1700
Data Index: 1245572 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9544. Min Act: -0.1700
Data Index: 129783 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9544. Min Act: -0.1700
Data Index: 476125 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0808. Min Range: -3.0808
Max Act: 2.9386. Min Act: -0.1700
Data Index: 425476 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19