Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6328. Min Act: -0.1700
Data Index: 8175405 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6484. Min Act: -0.1700
Data Index: 5988510 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6172. Min Act: -0.1700
Data Index: 6688273 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5858. Min Act: -0.1700
Data Index: 2658610 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.6015. Min Act: -0.1700
Data Index: 4436263 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5389. Min Act: -0.1700
Data Index: 2488711 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5232. Min Act: -0.1700
Data Index: 4633854 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5232. Min Act: -0.1700
Data Index: 7770750 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.5076. Min Act: -0.1700
Data Index: 5930277 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4919. Min Act: -0.1700
Data Index: 8005672 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4762. Min Act: -0.1700
Data Index: 4633855 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4762. Min Act: -0.1700
Data Index: 8604521 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4606. Min Act: -0.1700
Data Index: 1816405 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4606. Min Act: -0.1700
Data Index: 1061654 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4606. Min Act: -0.1700
Data Index: 5560422 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4449. Min Act: -0.1700
Data Index: 5944762 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4449. Min Act: -0.1700
Data Index: 8491856 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4449. Min Act: -0.1700
Data Index: 1996568 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4292. Min Act: -0.1700
Data Index: 7044213 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6484. Min Range: -3.6484
Max Act: 3.4136. Min Act: -0.1700
Data Index: 5074465 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19