Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.4307. Min Act: -0.1700
Data Index: 5761442 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.4619. Min Act: -0.1700
Data Index: 5990603 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.3682. Min Act: -0.1699
Data Index: 2001149 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.3369. Min Act: -0.1700
Data Index: 3438133 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.3056. Min Act: -0.1700
Data Index: 7185650 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.3056. Min Act: -0.1700
Data Index: 241137 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.3056. Min Act: -0.1700
Data Index: 8630036 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2744. Min Act: -0.1700
Data Index: 5312554 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2744. Min Act: -0.1700
Data Index: 4173306 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2431. Min Act: -0.1700
Data Index: 4272993 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2431. Min Act: -0.1700
Data Index: 7948584 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2431. Min Act: -0.1700
Data Index: 3769116 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.2119. Min Act: -0.1700
Data Index: 4590401 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1806. Min Act: -0.1700
Data Index: 27348 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1494. Min Act: -0.1700
Data Index: 7053259 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1806. Min Act: -0.1700
Data Index: 1985326 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1806. Min Act: -0.1700
Data Index: 992676 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1806. Min Act: -0.1700
Data Index: 7729148 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1494. Min Act: -0.1700
Data Index: 5159192 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4619. Min Range: -4.4619
Max Act: 4.1494. Min Act: -0.1700
Data Index: 3596605 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19