Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.8542. Min Act: -0.1700
Data Index: 57086 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.6355. Min Act: -0.1700
Data Index: 6516239 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.4480. Min Act: -0.1700
Data Index: 8493787 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.4792. Min Act: -0.1700
Data Index: 2725215 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.2917. Min Act: -0.1700
Data Index: 4469496 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.2292. Min Act: -0.1700
Data Index: 1527517 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.1980. Min Act: -0.1700
Data Index: 4720025 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 5766906 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.1355. Min Act: -0.1700
Data Index: 8758468 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.1355. Min Act: -0.1700
Data Index: 4348789 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 8078212 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0730. Min Act: -0.1700
Data Index: 7982218 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0417. Min Act: -0.1700
Data Index: 7401479 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0105. Min Act: -0.1700
Data Index: 5044634 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0417. Min Act: -0.1700
Data Index: 2625324 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0105. Min Act: -0.1700
Data Index: 179820 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0105. Min Act: -0.1700
Data Index: 393899 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8542. Min Range: -5.8542
Max Act: 5.0105. Min Act: -0.1700
Data Index: 849679 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8542. Min Range: -5.8542
Max Act: 4.9792. Min Act: -0.1700
Data Index: 5940370 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8542. Min Range: -5.8542
Max Act: 4.9480. Min Act: -0.1700
Data Index: 2312663 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19