Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.4026. Min Act: -0.1700
Data Index: 2300128 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.3714. Min Act: -0.1700
Data Index: 6264099 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.2151. Min Act: -0.1700
Data Index: 6007094 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.1214. Min Act: -0.1700
Data Index: 5804069 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4026. Min Range: -5.4026
Max Act: 5.0589. Min Act: -0.1700
Data Index: 3497851 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9964. Min Act: -0.1700
Data Index: 6047664 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9964. Min Act: -0.1700
Data Index: 8529172 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9651. Min Act: -0.1700
Data Index: 2670599 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.9026. Min Act: -0.1700
Data Index: 2237735 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 3635975 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 165223 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 2659218 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 767680 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 2198053 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8714. Min Act: -0.1700
Data Index: 5646451 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8401. Min Act: -0.1700
Data Index: 1459404 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8089. Min Act: -0.1700
Data Index: 3328206 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8401. Min Act: -0.1700
Data Index: 4289674 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8401. Min Act: -0.1700
Data Index: 333633 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4026. Min Range: -5.4026
Max Act: 4.8401. Min Act: -0.1700
Data Index: 6682272 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19