Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4778 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1636. Min Range: -7.1636
Max Act: 7.1636. Min Act: -0.1700
Data Index: 3885503 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.7261. Min Act: -0.1700
Data Index: 25708 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.6011. Min Act: -0.1700
Data Index: 8417254 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5386. Min Act: -0.1700
Data Index: 6495781 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5073. Min Act: -0.1700
Data Index: 6974554 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5073. Min Act: -0.1700
Data Index: 7516656 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5073. Min Act: -0.1700
Data Index: 3994304 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5073. Min Act: -0.1700
Data Index: 22597 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.5073. Min Act: -0.1700
Data Index: 1394448 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.4761. Min Act: -0.1700
Data Index: 2360042 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.4448. Min Act: -0.1700
Data Index: 778301 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.4448. Min Act: -0.1700
Data Index: 2852992 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3823. Min Act: -0.1700
Data Index: 621463 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3823. Min Act: -0.1700
Data Index: 4403808 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3823. Min Act: -0.1700
Data Index: 1292202 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3511. Min Act: -0.1700
Data Index: 3700456 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3198. Min Act: -0.1700
Data Index: 3155205 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3511. Min Act: -0.1700
Data Index: 6501384 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3511. Min Act: -0.1700
Data Index: 5589254 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1636. Min Range: -7.1636
Max Act: 6.3198. Min Act: -0.1700
Data Index: 7719381 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19