Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4910 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.5056. Min Act: -0.1700
Data Index: 7994365 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.2869. Min Act: -0.1700
Data Index: 5344184 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.2244. Min Act: -0.1700
Data Index: 8215855 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.2244. Min Act: -0.1700
Data Index: 1724302 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.1306. Min Act: -0.1700
Data Index: 4187308 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.1306. Min Act: -0.1700
Data Index: 4040277 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.0681. Min Act: -0.1700
Data Index: 5843424 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.0369. Min Act: -0.1700
Data Index: 7037318 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.0369. Min Act: -0.1700
Data Index: 7670548 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.0369. Min Act: -0.1700
Data Index: 8166628 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9744. Min Act: -0.1700
Data Index: 4440732 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9744. Min Act: -0.1700
Data Index: 5485626 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5056. Min Range: -7.5056
Max Act: 7.0056. Min Act: -0.1700
Data Index: 3544710 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9744. Min Act: -0.1700
Data Index: 3795124 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9744. Min Act: -0.1700
Data Index: 618419 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9744. Min Act: -0.1700
Data Index: 377339 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9431. Min Act: -0.1700
Data Index: 1574640 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9431. Min Act: -0.1700
Data Index: 5661355 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9119. Min Act: -0.1700
Data Index: 8312947 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5056. Min Range: -7.5056
Max Act: 6.9119. Min Act: -0.1700
Data Index: 158926 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19