Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6154 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.7962. Min Act: -0.1700
Data Index: 7564561 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.6087. Min Act: -0.1700
Data Index: 3101257 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.5462. Min Act: -0.1700
Data Index: 8817864 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.5149. Min Act: -0.1700
Data Index: 4462425 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.4837. Min Act: -0.1700
Data Index: 548456 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3899. Min Act: -0.1700
Data Index: 7233747 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3587. Min Act: -0.1700
Data Index: 4041651 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3274. Min Act: -0.1700
Data Index: 6141341 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3274. Min Act: -0.1700
Data Index: 3501609 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3274. Min Act: -0.1700
Data Index: 3131087 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.3274. Min Act: -0.1700
Data Index: 7151564 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2962. Min Act: -0.1700
Data Index: 1946612 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2649. Min Act: -0.1700
Data Index: 574833 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2337. Min Act: -0.1700
Data Index: 513815 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2337. Min Act: -0.1700
Data Index: 5979277 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2024. Min Act: -0.1700
Data Index: 5777917 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.1712. Min Act: -0.1700
Data Index: 7403694 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.1399. Min Act: -0.1700
Data Index: 5107289 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.2024. Min Act: -0.1700
Data Index: 6321306 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7962. Min Range: -6.7962
Max Act: 6.1399. Min Act: -0.1700
Data Index: 1008725 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19