Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.3435. Min Act: -0.1700
Data Index: 1194996 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.2810. Min Act: -0.1700
Data Index: 2531921 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.2810. Min Act: -0.1700
Data Index: 4148524 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.2498. Min Act: -0.1700
Data Index: 2646258 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.2810. Min Act: -0.1700
Data Index: 1342274 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.1873. Min Act: -0.1700
Data Index: 352203 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.0623. Min Act: -0.1700
Data Index: 8343473 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3435. Min Range: -5.3435
Max Act: 5.0623. Min Act: -0.1700
Data Index: 2559106 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9998. Min Act: -0.1700
Data Index: 736198 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9998. Min Act: -0.1700
Data Index: 7003051 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 3220831 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2568531 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2565749 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2805010 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 2417721 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9685. Min Act: -0.1700
Data Index: 3464291 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9373. Min Act: -0.1700
Data Index: 4906108 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9373. Min Act: -0.1700
Data Index: 2301981 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9373. Min Act: -0.1700
Data Index: 4367758 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3435. Min Range: -5.3435
Max Act: 4.9373. Min Act: -0.1700
Data Index: 2311826 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19