Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4136 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.5309. Min Act: -0.1700
Data Index: 8428011 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.5309. Min Act: -0.1700
Data Index: 1117060 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.3434. Min Act: -0.1700
Data Index: 4418878 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.3122. Min Act: -0.1700
Data Index: 205916 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.3122. Min Act: -0.1700
Data Index: 5609960 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.2497. Min Act: -0.1700
Data Index: 4840445 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1872. Min Act: -0.1700
Data Index: 853409 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1559. Min Act: -0.1700
Data Index: 7836936 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1559. Min Act: -0.1700
Data Index: 88358 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1559. Min Act: -0.1700
Data Index: 3636794 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1247. Min Act: -0.1700
Data Index: 1717657 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.1247. Min Act: -0.1700
Data Index: 2996500 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 4914333 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0934. Min Act: -0.1700
Data Index: 88364 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 1427827 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 8179679 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 5530415 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 1148115 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 7647084 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5309. Min Range: -5.5309
Max Act: 5.0622. Min Act: -0.1700
Data Index: 5289386 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19