Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5032 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.4670. Min Act: -0.1700
Data Index: 5785974 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.4670. Min Act: -0.1700
Data Index: 6920734 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.3420. Min Act: -0.1700
Data Index: 3189183 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.2170. Min Act: -0.1700
Data Index: 2245960 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.2170. Min Act: -0.1700
Data Index: 1337700 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1857. Min Act: -0.1700
Data Index: 3289166 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.2170. Min Act: -0.1700
Data Index: 3080145 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1545. Min Act: -0.1700
Data Index: 3657005 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1857. Min Act: -0.1700
Data Index: 2424766 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.2170. Min Act: -0.1700
Data Index: 763270 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1857. Min Act: -0.1700
Data Index: 488006 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1545. Min Act: -0.1700
Data Index: 5005939 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1232. Min Act: -0.1700
Data Index: 6202534 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1232. Min Act: -0.1700
Data Index: 73200 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.1232. Min Act: -0.1700
Data Index: 897770 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.0920. Min Act: -0.1700
Data Index: 7200291 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.0920. Min Act: -0.1700
Data Index: 4015980 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.0607. Min Act: -0.1700
Data Index: 2560422 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.0295. Min Act: -0.1700
Data Index: 5769413 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4670. Min Range: -6.4670
Max Act: 6.0295. Min Act: -0.1700
Data Index: 255641 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19