Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.4190. Min Act: -0.1700
Data Index: 6584581 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.3565. Min Act: -0.1700
Data Index: 7533621 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.2940. Min Act: -0.1700
Data Index: 8757872 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.2315. Min Act: -0.1700
Data Index: 2109106 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1377. Min Act: -0.1700
Data Index: 4463238 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1377. Min Act: -0.1700
Data Index: 612210 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.1065. Min Act: -0.1700
Data Index: 1859020 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0752. Min Act: -0.1700
Data Index: 8584654 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0752. Min Act: -0.1700
Data Index: 2792613 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0752. Min Act: -0.1700
Data Index: 3731590 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0752. Min Act: -0.1700
Data Index: 1681957 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0752. Min Act: -0.1700
Data Index: 6077192 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1243373 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0440. Min Act: -0.1700
Data Index: 7075204 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6424265 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0127. Min Act: -0.1700
Data Index: 149522 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4190. Min Range: -5.4190
Max Act: 5.0127. Min Act: -0.1700
Data Index: 2672058 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4190. Min Range: -5.4190
Max Act: 4.9815. Min Act: -0.1700
Data Index: 1923469 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4190. Min Range: -5.4190
Max Act: 4.9815. Min Act: -0.1700
Data Index: 1801601 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4190. Min Range: -5.4190
Max Act: 4.9502. Min Act: -0.1700
Data Index: 7162624 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19