Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.5415. Min Act: -0.1700
Data Index: 5563111 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.5102. Min Act: -0.1700
Data Index: 886533 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.5415. Min Act: -0.1700
Data Index: 5645867 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4790. Min Act: -0.1700
Data Index: 8444179 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4790. Min Act: -0.1700
Data Index: 8299096 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4790. Min Act: -0.1700
Data Index: 1697826 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 2643133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4477. Min Act: -0.1700
Data Index: 2198097 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 5029398 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 382872 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4477. Min Act: -0.1700
Data Index: 857862 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 2341026 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 2566547 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.4165. Min Act: -0.1700
Data Index: 8172541 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3852. Min Act: -0.1700
Data Index: 572591 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3852. Min Act: -0.1700
Data Index: 5686359 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3540. Min Act: -0.1700
Data Index: 4628609 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3540. Min Act: -0.1700
Data Index: 4193831 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3540. Min Act: -0.1700
Data Index: 5645863 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5415. Min Range: -5.5415
Max Act: 5.3540. Min Act: -0.1700
Data Index: 2208262 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19