Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5706 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.9183. Min Act: -0.1700
Data Index: 8409150 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.7933. Min Act: -0.1700
Data Index: 3456408 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.7308. Min Act: -0.1700
Data Index: 7128388 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6995. Min Act: -0.1700
Data Index: 497714 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6370. Min Act: -0.1700
Data Index: 5732887 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6683. Min Act: -0.1700
Data Index: 8266520 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6683. Min Act: -0.1700
Data Index: 7392711 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6683. Min Act: -0.1700
Data Index: 589265 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6370. Min Act: -0.1700
Data Index: 7867730 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6058. Min Act: -0.1700
Data Index: 3986475 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6058. Min Act: -0.1700
Data Index: 7408044 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6058. Min Act: -0.1700
Data Index: 1546066 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.6058. Min Act: -0.1700
Data Index: 5082383 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5745. Min Act: -0.1700
Data Index: 1512417 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5745. Min Act: -0.1700
Data Index: 2315360 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5745. Min Act: -0.1700
Data Index: 5267792 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5745. Min Act: -0.1700
Data Index: 8139903 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5745. Min Act: -0.1700
Data Index: 151615 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5433. Min Act: -0.1700
Data Index: 7830914 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9183. Min Range: -5.9183
Max Act: 5.5433. Min Act: -0.1700
Data Index: 4862883 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19