Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5215 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2248. Min Range: -7.2248
Max Act: 7.2248. Min Act: -0.1700
Data Index: 1915254 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2248. Min Range: -7.2248
Max Act: 7.1311. Min Act: -0.1700
Data Index: 1503427 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2248. Min Range: -7.2248
Max Act: 7.0373. Min Act: -0.1700
Data Index: 7562519 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2248. Min Range: -7.2248
Max Act: 7.0061. Min Act: -0.1700
Data Index: 1162915 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2248. Min Range: -7.2248
Max Act: 7.0061. Min Act: -0.1700
Data Index: 1538524 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.9748. Min Act: -0.1700
Data Index: 6946540 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.9436. Min Act: -0.1700
Data Index: 4443172 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8811. Min Act: -0.1700
Data Index: 8203106 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.9123. Min Act: -0.1700
Data Index: 4244591 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.9123. Min Act: -0.1700
Data Index: 5094856 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.9123. Min Act: -0.1700
Data Index: 4327123 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8811. Min Act: -0.1700
Data Index: 5154629 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8811. Min Act: -0.1700
Data Index: 7997891 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8811. Min Act: -0.1700
Data Index: 2232197 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8498. Min Act: -0.1700
Data Index: 8372762 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8186. Min Act: -0.1700
Data Index: 8722037 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8498. Min Act: -0.1700
Data Index: 3583519 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8186. Min Act: -0.1700
Data Index: 3639488 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.8186. Min Act: -0.1700
Data Index: 1332467 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2248. Min Range: -7.2248
Max Act: 6.7561. Min Act: -0.1700
Data Index: 6791516 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19