Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6354 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.9794. Min Act: -0.1700
Data Index: 2784371 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.6044. Min Act: -0.1700
Data Index: 2431040 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.5731. Min Act: -0.1700
Data Index: 5179951 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.4169. Min Act: -0.1700
Data Index: 1621648 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.3856. Min Act: -0.1700
Data Index: 8069491 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.3544. Min Act: -0.1700
Data Index: 5490656 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.3231. Min Act: -0.1700
Data Index: 7330190 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.2919. Min Act: -0.1700
Data Index: 8044328 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.2919. Min Act: -0.1700
Data Index: 4421245 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.2294. Min Act: -0.1700
Data Index: 512677 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1981. Min Act: -0.1700
Data Index: 3358518 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1981. Min Act: -0.1700
Data Index: 4454717 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1981. Min Act: -0.1700
Data Index: 5447629 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 5897359 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 2937187 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 547321 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1669. Min Act: -0.1700
Data Index: 2059963 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1356. Min Act: -0.1700
Data Index: 6905618 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1356. Min Act: -0.1700
Data Index: 2335866 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9794. Min Range: -5.9794
Max Act: 5.1356. Min Act: -0.1700
Data Index: 7190489 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19