Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.5884. Min Act: -0.1700
Data Index: 2596868 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.5415. Min Act: -0.1700
Data Index: 1084120 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4788. Min Act: -0.1700
Data Index: 5162391 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4788. Min Act: -0.1700
Data Index: 2756223 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4318. Min Act: -0.1700
Data Index: 6754222 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4161. Min Act: -0.1700
Data Index: 1556901 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4005. Min Act: -0.1700
Data Index: 2087299 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.4005. Min Act: -0.1700
Data Index: 7937517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3848. Min Act: -0.1700
Data Index: 4518749 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3691. Min Act: -0.1700
Data Index: 4619939 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3691. Min Act: -0.1700
Data Index: 6503243 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3220. Min Act: -0.1700
Data Index: 2426329 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3377. Min Act: -0.1700
Data Index: 3356929 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3220. Min Act: -0.1700
Data Index: 7696194 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3691. Min Act: -0.1700
Data Index: 5186496 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3691. Min Act: -0.1700
Data Index: 827375 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3534. Min Act: -0.1700
Data Index: 789864 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3534. Min Act: -0.1700
Data Index: 2823970 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3534. Min Act: -0.1700
Data Index: 467404 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5884. Min Range: -3.5884
Max Act: 3.3534. Min Act: -0.1700
Data Index: 1658683 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19