Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.2641. Min Act: -0.1700
Data Index: 5774569 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0766. Min Act: -0.1699
Data Index: 4753746 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0766. Min Act: -0.1700
Data Index: 1369830 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0453. Min Act: -0.1700
Data Index: 2994099 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0453. Min Act: -0.1700
Data Index: 4273656 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0141. Min Act: -0.1697
Data Index: 5300016 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2641. Min Range: -5.2641
Max Act: 5.0141. Min Act: -0.1694
Data Index: 3339728 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.9828. Min Act: -0.1700
Data Index: 856924 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.9203. Min Act: -0.1700
Data Index: 2356817 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8891. Min Act: -0.1700
Data Index: 2783065 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.9203. Min Act: -0.1699
Data Index: 5644348 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.9203. Min Act: -0.1700
Data Index: 6604220 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8891. Min Act: -0.1700
Data Index: 2678146 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8891. Min Act: -0.1700
Data Index: 1423449 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8578. Min Act: -0.1689
Data Index: 532360 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8891. Min Act: -0.1700
Data Index: 197357 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8578. Min Act: -0.1693
Data Index: 6504986 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8578. Min Act: -0.1700
Data Index: 8138270 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8578. Min Act: -0.1700
Data Index: 6004471 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2641. Min Range: -5.2641
Max Act: 4.8578. Min Act: -0.1700
Data Index: 4444728 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19