Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2548. Min Range: -6.2548
Max Act: 6.2548. Min Act: -0.1700
Data Index: 7545283 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2548. Min Range: -6.2548
Max Act: 6.0048. Min Act: -0.1700
Data Index: 7335174 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2548. Min Range: -6.2548
Max Act: 6.0048. Min Act: -0.1700
Data Index: 3519445 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.9423. Min Act: -0.1700
Data Index: 2631559 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.9111. Min Act: -0.1700
Data Index: 8086588 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.8798. Min Act: -0.1700
Data Index: 1431430 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.8798. Min Act: -0.1700
Data Index: 1852452 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.8798. Min Act: -0.1700
Data Index: 5591051 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.8173. Min Act: -0.1700
Data Index: 4558804 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7548. Min Act: -0.1700
Data Index: 7744222 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7548. Min Act: -0.1700
Data Index: 925953 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7236. Min Act: -0.1700
Data Index: 79229 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7548. Min Act: -0.1700
Data Index: 1782253 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7548. Min Act: -0.1700
Data Index: 3605236 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7861. Min Act: -0.1700
Data Index: 1131901 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7236. Min Act: -0.1700
Data Index: 5424660 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7236. Min Act: -0.1700
Data Index: 5246266 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7236. Min Act: -0.1700
Data Index: 183566 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.7236. Min Act: -0.1700
Data Index: 3388011 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2548. Min Range: -6.2548
Max Act: 5.6923. Min Act: -0.1700
Data Index: 7829250 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19