Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0538. Min Range: -6.0538
Max Act: 6.0538. Min Act: -0.1700
Data Index: 7013835 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0538. Min Range: -6.0538
Max Act: 6.0225. Min Act: -0.1700
Data Index: 8659293 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0538. Min Range: -6.0538
Max Act: 6.0225. Min Act: -0.1700
Data Index: 3926930 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9913. Min Act: -0.1700
Data Index: 5126940 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9600. Min Act: -0.1700
Data Index: 7140617 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9600. Min Act: -0.1700
Data Index: 1558839 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9600. Min Act: -0.1700
Data Index: 4172795 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9288. Min Act: -0.1700
Data Index: 2714144 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9288. Min Act: -0.1700
Data Index: 3063772 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.9288. Min Act: -0.1700
Data Index: 8179698 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8975. Min Act: -0.1700
Data Index: 3052741 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8663. Min Act: -0.1700
Data Index: 3346170 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8975. Min Act: -0.1700
Data Index: 877608 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8663. Min Act: -0.1700
Data Index: 2778705 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8350. Min Act: -0.1700
Data Index: 756185 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8350. Min Act: -0.1700
Data Index: 4377487 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8038. Min Act: -0.1700
Data Index: 1262545 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7248474 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.7725. Min Act: -0.1700
Data Index: 1235558 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0538. Min Range: -6.0538
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7254102 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19