Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2410. Min Range: -5.2410
Max Act: 5.2410. Min Act: -0.1700
Data Index: 8654917 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2410. Min Range: -5.2410
Max Act: 5.1160. Min Act: -0.1700
Data Index: 5119493 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2410. Min Range: -5.2410
Max Act: 5.0223. Min Act: -0.1700
Data Index: 3025919 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.9910. Min Act: -0.1699
Data Index: 6025956 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2410. Min Range: -5.2410
Max Act: 5.0223. Min Act: -0.1700
Data Index: 2282948 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.9910. Min Act: -0.1700
Data Index: 7468564 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 8174001 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.9598. Min Act: -0.1700
Data Index: 631951 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8035. Min Act: -0.1700
Data Index: 3237469 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8973. Min Act: -0.1700
Data Index: 2280558 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8973. Min Act: -0.1700
Data Index: 7342851 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8973. Min Act: -0.1700
Data Index: 6110152 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2074000 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8973. Min Act: -0.1700
Data Index: 4173416 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 5078294 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8660. Min Act: -0.1699
Data Index: 6346189 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8348. Min Act: -0.1700
Data Index: 5260182 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8660. Min Act: -0.1700
Data Index: 6004737 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8035. Min Act: -0.1700
Data Index: 7542966 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2410. Min Range: -5.2410
Max Act: 4.8660. Min Act: -0.1697
Data Index: 5583830 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19