Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5978 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.8445. Min Act: -0.1700
Data Index: 6814180 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.8133. Min Act: -0.1700
Data Index: 5595420 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.8133. Min Act: -0.1700
Data Index: 1180983 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.6570. Min Act: -0.1700
Data Index: 4747310 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.6258. Min Act: -0.1700
Data Index: 2160338 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.6258. Min Act: -0.1700
Data Index: 3344226 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.6258. Min Act: -0.1700
Data Index: 1448642 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.5008. Min Act: -0.1700
Data Index: 883184 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.4695. Min Act: -0.1700
Data Index: 8397260 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.4383. Min Act: -0.1700
Data Index: 4447054 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3445. Min Act: -0.1700
Data Index: 6614237 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3758. Min Act: -0.1700
Data Index: 1256412 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3445. Min Act: -0.1700
Data Index: 6142599 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3445. Min Act: -0.1700
Data Index: 8566243 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3445. Min Act: -0.1700
Data Index: 4152015 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.2820. Min Act: -0.1700
Data Index: 840196 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3133. Min Act: -0.1700
Data Index: 4394759 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.3133. Min Act: -0.1700
Data Index: 1045583 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.2820. Min Act: -0.1700
Data Index: 2293594 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8445. Min Range: -6.8445
Max Act: 6.2820. Min Act: -0.1700
Data Index: 8566223 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19