Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4920 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0348. Min Range: -7.0348
Max Act: 7.0348. Min Act: -0.1700
Data Index: 978523 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.8473. Min Act: -0.1700
Data Index: 3329709 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.9098. Min Act: -0.1700
Data Index: 1397151 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.8473. Min Act: -0.1700
Data Index: 3547264 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.8473. Min Act: -0.1700
Data Index: 1602048 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5915666 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7535. Min Act: -0.1700
Data Index: 7949892 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7223. Min Act: -0.1700
Data Index: 5720409 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.8160. Min Act: -0.1700
Data Index: 495745 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7535. Min Act: -0.1700
Data Index: 1077767 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7223. Min Act: -0.1700
Data Index: 5862982 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7535. Min Act: -0.1700
Data Index: 5132959 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.7223. Min Act: -0.1700
Data Index: 7936146 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7199465 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6598. Min Act: -0.1700
Data Index: 1064200 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6598. Min Act: -0.1700
Data Index: 1692542 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6598. Min Act: -0.1700
Data Index: 4083005 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6285. Min Act: -0.1700
Data Index: 5577020 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.6285. Min Act: -0.1700
Data Index: 3614903 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0348. Min Range: -7.0348
Max Act: 6.5973. Min Act: -0.1700
Data Index: 3810140 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19