Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7734. Min Act: -0.1700
Data Index: 6050951 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.8046. Min Act: -0.1700
Data Index: 3028838 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.8046. Min Act: -0.1700
Data Index: 2362942 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7421. Min Act: -0.1700
Data Index: 4515325 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7421. Min Act: -0.1700
Data Index: 8228207 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7109. Min Act: -0.1700
Data Index: 3461661 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7109. Min Act: -0.1700
Data Index: 138555 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 320349 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7109. Min Act: -0.1700
Data Index: 4327718 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.7109. Min Act: -0.1700
Data Index: 5500099 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 5477796 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 8572953 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 6001575 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 6747627 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6171. Min Act: -0.1700
Data Index: 6667297 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6171. Min Act: -0.1700
Data Index: 2705686 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 8492764 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.5859. Min Act: -0.1700
Data Index: 7006371 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6171. Min Act: -0.1700
Data Index: 6099319 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8046. Min Range: -6.8046
Max Act: 6.6484. Min Act: -0.1700
Data Index: 8036641 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19