Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 299 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.5237. Min Act: -0.1700
Data Index: 3020642 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.4925. Min Act: -0.1700
Data Index: 4284025 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.5237. Min Act: -0.1700
Data Index: 5017777 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.4612. Min Act: -0.1700
Data Index: 6201197 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.4300. Min Act: -0.1700
Data Index: 2883051 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3987. Min Act: -0.1700
Data Index: 8118502 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3987. Min Act: -0.1700
Data Index: 4009373 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 5342181 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3987. Min Act: -0.1700
Data Index: 8425520 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3987. Min Act: -0.1700
Data Index: 8328201 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 6988070 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3675. Min Act: -0.1700
Data Index: 717039 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3675. Min Act: -0.1699
Data Index: 254812 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 1897503 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 7275844 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 4192299 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3675. Min Act: -0.1700
Data Index: 7936050 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3362. Min Act: -0.1700
Data Index: 1310173 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.3050. Min Act: -0.1700
Data Index: 5017775 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5237. Min Range: -4.5237
Max Act: 4.2737. Min Act: -0.1700
Data Index: 6068726 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19