Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.1654. Min Act: -0.1700
Data Index: 3979333 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.1487. Min Act: -0.1700
Data Index: 1625578 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.1320. Min Act: -0.1700
Data Index: 171092 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.1153. Min Act: -0.1700
Data Index: 1944889 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0986. Min Act: -0.1700
Data Index: 4105225 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0818. Min Act: -0.1700
Data Index: 1740520 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0482. Min Act: -0.1700
Data Index: 8542426 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0314. Min Act: -0.1700
Data Index: 1625567 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0314. Min Act: -0.1700
Data Index: 3368140 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0314. Min Act: -0.1700
Data Index: 2850516 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0314. Min Act: -0.1700
Data Index: 2467913 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0229. Min Act: -0.1695
Data Index: 7798987 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0061. Min Act: -0.1700
Data Index: 4367081 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0145. Min Act: -0.1700
Data Index: 7400136 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0145. Min Act: -0.1700
Data Index: 7542871 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0145. Min Act: -0.1700
Data Index: 2026611 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0061. Min Act: -0.1700
Data Index: 8267604 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0145. Min Act: -0.1700
Data Index: 7028308 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0061. Min Act: -0.1700
Data Index: 8166051 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1654. Min Range: -2.1654
Max Act: 2.0061. Min Act: -0.1700
Data Index: 3670928 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19