Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1972. Min Range: -5.1972
Max Act: 5.1972. Min Act: -0.1700
Data Index: 339 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1972. Min Range: -5.1972
Max Act: 5.1035. Min Act: -0.1700
Data Index: 6167526 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1972. Min Range: -5.1972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 6339085 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1972. Min Range: -5.1972
Max Act: 5.0097. Min Act: -0.1700
Data Index: 4173110 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9785. Min Act: -0.1700
Data Index: 507870 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 1575159 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 3884578 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 329 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 6381867 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9472. Min Act: -0.1700
Data Index: 6576791 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9160. Min Act: -0.1700
Data Index: 6381871 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.9160. Min Act: -0.1700
Data Index: 7102420 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8847. Min Act: -0.1700
Data Index: 537524 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8535. Min Act: -0.1700
Data Index: 6976264 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8847. Min Act: -0.1700
Data Index: 4173109 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4020503 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8222. Min Act: -0.1700
Data Index: 6958496 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8222. Min Act: -0.1700
Data Index: 2024432 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.8535. Min Act: -0.1700
Data Index: 4498482 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1972. Min Range: -5.1972
Max Act: 4.7597. Min Act: -0.1700
Data Index: 4211737 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19