Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 827 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.4068. Min Act: -0.1700
Data Index: 2130677 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.3755. Min Act: -0.1700
Data Index: 7526761 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.1568. Min Act: -0.1700
Data Index: 3044480 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.0317. Min Act: -0.1700
Data Index: 7564315 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.0005. Min Act: -0.1700
Data Index: 6548159 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.0005. Min Act: -0.1700
Data Index: 558465 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4068. Min Range: -4.4068
Max Act: 4.0005. Min Act: -0.1700
Data Index: 7931645 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9692. Min Act: -0.1700
Data Index: 1712271 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9379. Min Act: -0.1700
Data Index: 2322376 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9379. Min Act: -0.1700
Data Index: 7959276 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9067. Min Act: -0.1700
Data Index: 749251 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9067. Min Act: -0.1700
Data Index: 7998157 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9379. Min Act: -0.1700
Data Index: 4959022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.9379. Min Act: -0.1700
Data Index: 1945776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8754. Min Act: -0.1700
Data Index: 2322368 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8598. Min Act: -0.1700
Data Index: 5989515 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8598. Min Act: -0.1700
Data Index: 8175425 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8441. Min Act: -0.1700
Data Index: 3703544 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8754. Min Act: -0.1700
Data Index: 7527966 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4068. Min Range: -4.4068
Max Act: 3.8129. Min Act: -0.1700
Data Index: 2510305 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19