Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 4925847 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.7369. Min Act: -0.1700
Data Index: 233378 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.7369. Min Act: -0.1700
Data Index: 7710042 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.7369. Min Act: -0.1700
Data Index: 2057901 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.7057. Min Act: -0.1700
Data Index: 1875871 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.4557. Min Act: -0.1700
Data Index: 2906955 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.4557. Min Act: -0.1700
Data Index: 2591959 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3619. Min Act: -0.1700
Data Index: 6015741 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3619. Min Act: -0.1700
Data Index: 3065477 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3619. Min Act: -0.1700
Data Index: 2707979 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3307. Min Act: -0.1700
Data Index: 5201142 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3619. Min Act: -0.1700
Data Index: 6449943 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3307. Min Act: -0.1700
Data Index: 5173375 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3619. Min Act: -0.1700
Data Index: 8566240 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.3307. Min Act: -0.1700
Data Index: 1089669 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.2994. Min Act: -0.1700
Data Index: 4988083 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.2994. Min Act: -0.1700
Data Index: 3197069 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.2369. Min Act: -0.1700
Data Index: 6082513 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.2057. Min Act: -0.1700
Data Index: 3963051 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9557. Min Range: -5.9557
Max Act: 5.2057. Min Act: -0.1700
Data Index: 5879305 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19