Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.3539. Min Act: -0.1700
Data Index: 3522179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.3227. Min Act: -0.1700
Data Index: 45670 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.3227. Min Act: -0.1700
Data Index: 3602142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.3227. Min Act: -0.1700
Data Index: 7551159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 5507051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4857429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 3216839 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 7279263 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 4033722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2914. Min Act: -0.1700
Data Index: 6266309 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 7009743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 6471909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 8379819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 3951517 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 3602921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5530877 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5519792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2289. Min Act: -0.1700
Data Index: 2014132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2289. Min Act: -0.1700
Data Index: 1462516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3539. Min Range: -5.3539
Max Act: 5.2289. Min Act: -0.1700
Data Index: 1492238 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19