Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2421. Min Range: -5.2421
Max Act: 5.2421. Min Act: -0.1700
Data Index: 4318078 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2421. Min Range: -5.2421
Max Act: 5.0234. Min Act: -0.1700
Data Index: 6623274 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.8046. Min Act: -0.1700
Data Index: 5684273 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.8359. Min Act: -0.1700
Data Index: 3299197 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7421. Min Act: -0.1700
Data Index: 2749294 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7421. Min Act: -0.1700
Data Index: 6721418 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7109. Min Act: -0.1700
Data Index: 1736889 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7109. Min Act: -0.1700
Data Index: 7096359 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1335079 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1390235 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6796. Min Act: -0.1700
Data Index: 3251895 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7109. Min Act: -0.1700
Data Index: 695218 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.7109. Min Act: -0.1700
Data Index: 8344162 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6484. Min Act: -0.1700
Data Index: 7786363 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1329388 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6484. Min Act: -0.1700
Data Index: 4798442 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6171. Min Act: -0.1700
Data Index: 6506890 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6171. Min Act: -0.1700
Data Index: 2942017 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6484. Min Act: -0.1700
Data Index: 2587794 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2421. Min Range: -5.2421
Max Act: 4.6171. Min Act: -0.1700
Data Index: 7214197 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19