Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0808. Min Range: -5.0808
Max Act: 5.0808. Min Act: -0.1700
Data Index: 5259384 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.9558. Min Act: -0.1700
Data Index: 5259381 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.9245. Min Act: -0.1700
Data Index: 350787 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8308. Min Act: -0.1700
Data Index: 5259386 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8620. Min Act: -0.1700
Data Index: 3456314 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8308. Min Act: -0.1700
Data Index: 6758434 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8308. Min Act: -0.1700
Data Index: 5762427 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.8308. Min Act: -0.1700
Data Index: 3583336 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2910271 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7683. Min Act: -0.1700
Data Index: 6863663 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7370. Min Act: -0.1700
Data Index: 8264692 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7370. Min Act: -0.1700
Data Index: 6598323 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7058. Min Act: -0.1700
Data Index: 1945144 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2507613 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7058. Min Act: -0.1700
Data Index: 2899061 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7058. Min Act: -0.1700
Data Index: 3869392 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.6745. Min Act: -0.1700
Data Index: 4579437 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.6745. Min Act: -0.1700
Data Index: 1060243 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.7058. Min Act: -0.1700
Data Index: 3424092 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0808. Min Range: -5.0808
Max Act: 4.6745. Min Act: -0.1700
Data Index: 181121 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19