Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.7508. Min Act: -0.1700
Data Index: 4034177 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.5945. Min Act: -0.1700
Data Index: 8126435 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.4695. Min Act: -0.1700
Data Index: 6378937 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.4383. Min Act: -0.1700
Data Index: 1835762 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.3445. Min Act: -0.1700
Data Index: 3215220 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.3445. Min Act: -0.1700
Data Index: 2122414 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.3133. Min Act: -0.1700
Data Index: 2581617 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.2820. Min Act: -0.1700
Data Index: 427796 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.2820. Min Act: -0.1700
Data Index: 2337590 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.2508. Min Act: -0.1700
Data Index: 686261 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.1883. Min Act: -0.1700
Data Index: 405441 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0945. Min Act: -0.1700
Data Index: 6506387 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.1258. Min Act: -0.1700
Data Index: 5145422 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.1258. Min Act: -0.1700
Data Index: 7093646 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.1258. Min Act: -0.1700
Data Index: 2733364 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0945. Min Act: -0.1700
Data Index: 6623589 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0945. Min Act: -0.1700
Data Index: 4853738 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0945. Min Act: -0.1700
Data Index: 7093649 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0945. Min Act: -0.1700
Data Index: 715164 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7508. Min Range: -6.7508
Max Act: 6.0633. Min Act: -0.1700
Data Index: 3574295 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19