Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.9314. Min Act: -0.1700
Data Index: 3670289 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.8064. Min Act: -0.1700
Data Index: 4695039 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.6502. Min Act: -0.1700
Data Index: 8575231 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.4939. Min Act: -0.1700
Data Index: 297904 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.4314. Min Act: -0.1700
Data Index: 4426297 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.4314. Min Act: -0.1700
Data Index: 4819653 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2752. Min Act: -0.1700
Data Index: 3167748 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2439. Min Act: -0.1700
Data Index: 7649276 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2752. Min Act: -0.1700
Data Index: 3167752 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2127. Min Act: -0.1700
Data Index: 727726 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2127. Min Act: -0.1700
Data Index: 5579116 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.2127. Min Act: -0.1700
Data Index: 6842913 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.1814. Min Act: -0.1700
Data Index: 4426298 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.1189. Min Act: -0.1700
Data Index: 1534709 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.1189. Min Act: -0.1700
Data Index: 1808354 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.0877. Min Act: -0.1700
Data Index: 1534710 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.0877. Min Act: -0.1700
Data Index: 7657061 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.0564. Min Act: -0.1700
Data Index: 7845540 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9314. Min Range: -7.9314
Max Act: 7.0252. Min Act: -0.1700
Data Index: 1940001 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9314. Min Range: -7.9314
Max Act: 6.9939. Min Act: -0.1700
Data Index: 1534708 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19