Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.5322. Min Act: -0.1700
Data Index: 1784781 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.2510. Min Act: -0.1700
Data Index: 4607738 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.2510. Min Act: -0.1700
Data Index: 3324548 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.2197. Min Act: -0.1700
Data Index: 6077016 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.2510. Min Act: -0.1700
Data Index: 3877205 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.2197. Min Act: -0.1700
Data Index: 1281380 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.1572. Min Act: -0.1700
Data Index: 3975157 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.1885. Min Act: -0.1700
Data Index: 5538540 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.1572. Min Act: -0.1700
Data Index: 8241477 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.1260. Min Act: -0.1700
Data Index: 8233849 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.1260. Min Act: -0.1700
Data Index: 3209150 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0947. Min Act: -0.1700
Data Index: 4674291 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0947. Min Act: -0.1700
Data Index: 709025 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0947. Min Act: -0.1700
Data Index: 5475969 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0947. Min Act: -0.1700
Data Index: 7879470 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0947. Min Act: -0.1700
Data Index: 3621697 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4202714 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7793476 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0322. Min Act: -0.1700
Data Index: 4563302 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5322. Min Range: -5.5322
Max Act: 5.0635. Min Act: -0.1700
Data Index: 7583928 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19