Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5256 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.6764. Min Act: -0.1700
Data Index: 1790579 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.6139. Min Act: -0.1700
Data Index: 1905870 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.5201. Min Act: -0.1700
Data Index: 1275553 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.5201. Min Act: -0.1700
Data Index: 2715727 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.4889. Min Act: -0.1700
Data Index: 6874330 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.4889. Min Act: -0.1700
Data Index: 5937444 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.4576. Min Act: -0.1700
Data Index: 3723773 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.4576. Min Act: -0.1700
Data Index: 2027953 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.3951. Min Act: -0.1700
Data Index: 7335423 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.3014. Min Act: -0.1700
Data Index: 2627416 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2701. Min Act: -0.1700
Data Index: 1495187 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.3014. Min Act: -0.1700
Data Index: 7462109 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2701. Min Act: -0.1700
Data Index: 3930515 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2701. Min Act: -0.1700
Data Index: 2534097 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2389. Min Act: -0.1700
Data Index: 6900330 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2076. Min Act: -0.1700
Data Index: 1331465 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.2076. Min Act: -0.1700
Data Index: 5637068 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.1451. Min Act: -0.1700
Data Index: 8252738 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.1764. Min Act: -0.1700
Data Index: 4552872 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6764. Min Range: -5.6764
Max Act: 5.1764. Min Act: -0.1700
Data Index: 8405437 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19