Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.5881. Min Act: -0.1700
Data Index: 3001012 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.5881. Min Act: -0.1700
Data Index: 4095646 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.5568. Min Act: -0.1700
Data Index: 50757 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4318. Min Act: -0.1700
Data Index: 8715945 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4631. Min Act: -0.1700
Data Index: 7080262 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4318. Min Act: -0.1700
Data Index: 4501315 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4318. Min Act: -0.1700
Data Index: 5485087 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4006. Min Act: -0.1700
Data Index: 4211749 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3693. Min Act: -0.1700
Data Index: 2061833 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4006. Min Act: -0.1700
Data Index: 1368965 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.4006. Min Act: -0.1700
Data Index: 835760 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3693. Min Act: -0.1700
Data Index: 7704080 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3381. Min Act: -0.1700
Data Index: 2261967 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3693. Min Act: -0.1700
Data Index: 1154097 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3693. Min Act: -0.1700
Data Index: 765494 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3693. Min Act: -0.1700
Data Index: 1748935 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3381. Min Act: -0.1700
Data Index: 2597895 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3381. Min Act: -0.1700
Data Index: 7927494 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3381. Min Act: -0.1700
Data Index: 4981497 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5881. Min Range: -5.5881
Max Act: 5.3068. Min Act: -0.1700
Data Index: 6719657 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19