Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.8141. Min Act: -0.1700
Data Index: 5504267 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.5016. Min Act: -0.1700
Data Index: 4494937 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.4078. Min Act: -0.1700
Data Index: 5504268 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.4391. Min Act: -0.1700
Data Index: 3015537 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.4391. Min Act: -0.1700
Data Index: 810750 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.3141. Min Act: -0.1700
Data Index: 8414661 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2828. Min Act: -0.1700
Data Index: 714294 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5494249 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2516. Min Act: -0.1700
Data Index: 1211804 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2516. Min Act: -0.1700
Data Index: 6870944 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2828. Min Act: -0.1700
Data Index: 847615 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2203. Min Act: -0.1700
Data Index: 498176 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2828. Min Act: -0.1700
Data Index: 5478432 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2203. Min Act: -0.1700
Data Index: 1579359 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2516. Min Act: -0.1700
Data Index: 5231921 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2203. Min Act: -0.1700
Data Index: 5085500 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2203. Min Act: -0.1700
Data Index: 4178039 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.2203. Min Act: -0.1700
Data Index: 4242743 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.1266. Min Act: -0.1700
Data Index: 3439600 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8141. Min Range: -6.8141
Max Act: 6.1578. Min Act: -0.1700
Data Index: 3835168 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19