Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.5686. Min Act: -0.1700
Data Index: 8162450 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.2248. Min Act: -0.1700
Data Index: 912930 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.1311. Min Act: -0.1700
Data Index: 1027666 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.0686. Min Act: -0.1700
Data Index: 3825285 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.0686. Min Act: -0.1700
Data Index: 7222087 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.0373. Min Act: -0.1700
Data Index: 4783963 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.0061. Min Act: -0.1700
Data Index: 8612012 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5686. Min Range: -6.5686
Max Act: 6.0061. Min Act: -0.1700
Data Index: 8803406 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9748. Min Act: -0.1700
Data Index: 3091800 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9436. Min Act: -0.1700
Data Index: 4057151 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9436. Min Act: -0.1700
Data Index: 353002 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9436. Min Act: -0.1700
Data Index: 7606572 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9123. Min Act: -0.1700
Data Index: 4796958 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9436. Min Act: -0.1700
Data Index: 689790 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.9123. Min Act: -0.1700
Data Index: 5143734 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.8811. Min Act: -0.1700
Data Index: 5981497 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.8811. Min Act: -0.1700
Data Index: 1659300 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.8498. Min Act: -0.1700
Data Index: 6943948 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.8186. Min Act: -0.1700
Data Index: 409503 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5686. Min Range: -6.5686
Max Act: 5.8186. Min Act: -0.1700
Data Index: 7567689 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19