Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.2602. Min Act: -0.1700
Data Index: 6785287 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.2337. Min Act: -0.1700
Data Index: 2570962 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1985. Min Act: -0.1700
Data Index: 3979718 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1897. Min Act: -0.1700
Data Index: 2852835 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1721. Min Act: -0.1700
Data Index: 8549249 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1457. Min Act: -0.1700
Data Index: 6604904 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1457. Min Act: -0.1700
Data Index: 8068577 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1457. Min Act: -0.1700
Data Index: 4146956 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1370. Min Act: -0.1700
Data Index: 4049253 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1370. Min Act: -0.1700
Data Index: 7790296 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1282. Min Act: -0.1700
Data Index: 1779259 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1282. Min Act: -0.1700
Data Index: 7890128 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1194. Min Act: -0.1700
Data Index: 4934769 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1194. Min Act: -0.1700
Data Index: 3313021 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1194. Min Act: -0.1700
Data Index: 855386 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1194. Min Act: -0.1700
Data Index: 4892185 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1019. Min Act: -0.1700
Data Index: 8394830 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1106. Min Act: -0.1700
Data Index: 4142888 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1106. Min Act: -0.1700
Data Index: 4112047 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2602. Min Range: -1.2602
Max Act: 1.1106. Min Act: -0.1700
Data Index: 5324959 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19