Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.3427. Min Act: -0.1700
Data Index: 2972719 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.2802. Min Act: -0.1700
Data Index: 7152258 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.2802. Min Act: -0.1700
Data Index: 4701350 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.2489. Min Act: -0.1700
Data Index: 1021086 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.1864. Min Act: -0.1700
Data Index: 2845175 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.1239. Min Act: -0.1700
Data Index: 6472148 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3427. Min Range: -7.3427
Max Act: 7.0302. Min Act: -0.1700
Data Index: 6042018 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.9989. Min Act: -0.1700
Data Index: 3755764 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.9677. Min Act: -0.1700
Data Index: 3557185 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.9677. Min Act: -0.1700
Data Index: 7435372 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.9052. Min Act: -0.1700
Data Index: 8638529 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8427. Min Act: -0.1700
Data Index: 7701222 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8427. Min Act: -0.1700
Data Index: 1415915 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8427. Min Act: -0.1700
Data Index: 7764005 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8427. Min Act: -0.1700
Data Index: 8125401 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8114. Min Act: -0.1700
Data Index: 6691672 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8114. Min Act: -0.1700
Data Index: 1736345 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.7802. Min Act: -0.1700
Data Index: 2808102 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8114. Min Act: -0.1700
Data Index: 2273889 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3427. Min Range: -7.3427
Max Act: 6.8114. Min Act: -0.1700
Data Index: 5739780 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19