Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.4578. Min Act: -0.1700
Data Index: 8386684 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.4266. Min Act: -0.1700
Data Index: 2848287 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.3016. Min Act: -0.1700
Data Index: 2628366 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.1453. Min Act: -0.1700
Data Index: 1786530 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0828. Min Act: -0.1700
Data Index: 1264766 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0828. Min Act: -0.1700
Data Index: 3049185 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0828. Min Act: -0.1700
Data Index: 5908045 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0828. Min Act: -0.1700
Data Index: 2614297 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0828. Min Act: -0.1700
Data Index: 7960014 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0203. Min Act: -0.1700
Data Index: 1363176 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0516. Min Act: -0.1700
Data Index: 7140897 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0516. Min Act: -0.1700
Data Index: 447333 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9891. Min Act: -0.1700
Data Index: 2619108 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4578. Min Range: -5.4578
Max Act: 5.0203. Min Act: -0.1700
Data Index: 2628354 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 862627 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 5898211 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9266. Min Act: -0.1700
Data Index: 6484120 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.9578. Min Act: -0.1700
Data Index: 5340248 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8953. Min Act: -0.1700
Data Index: 2018829 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4578. Min Range: -5.4578
Max Act: 4.8953. Min Act: -0.1700
Data Index: 3520413 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19