Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.6873. Min Act: -0.1700
Data Index: 7042932 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.6248. Min Act: -0.1700
Data Index: 992311 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.5623. Min Act: -0.1700
Data Index: 6025785 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4998. Min Act: -0.1700
Data Index: 6581600 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4373. Min Act: -0.1700
Data Index: 3831839 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4373. Min Act: -0.1700
Data Index: 8069875 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4373. Min Act: -0.1700
Data Index: 5871179 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4373. Min Act: -0.1700
Data Index: 2508631 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.4373. Min Act: -0.1700
Data Index: 4016428 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 3148549 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3123. Min Act: -0.1700
Data Index: 5612980 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 5732996 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 988449 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 3336958 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 5107010 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 2253516 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 2364581 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3748. Min Act: -0.1700
Data Index: 2375237 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3123. Min Act: -0.1700
Data Index: 3368424 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6873. Min Range: -10.6873
Max Act: 10.3123. Min Act: -0.1700
Data Index: 3533486 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19