Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.9648. Min Act: -0.1700
Data Index: 7101169 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.8711. Min Act: -0.1700
Data Index: 2874670 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.8711. Min Act: -0.1700
Data Index: 5461796 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.7773. Min Act: -0.1700
Data Index: 6586817 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.6523. Min Act: -0.1700
Data Index: 998800 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.5898. Min Act: -0.1700
Data Index: 957109 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.6211. Min Act: -0.1700
Data Index: 2548305 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.5273. Min Act: -0.1700
Data Index: 7909201 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.5273. Min Act: -0.1700
Data Index: 2570122 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4961. Min Act: -0.1700
Data Index: 5658581 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4961. Min Act: -0.1700
Data Index: 3472127 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4961. Min Act: -0.1700
Data Index: 474706 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4961. Min Act: -0.1700
Data Index: 2955591 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4648. Min Act: -0.1700
Data Index: 1776610 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4648. Min Act: -0.1700
Data Index: 5333025 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4336. Min Act: -0.1700
Data Index: 7798647 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.3711. Min Act: -0.1700
Data Index: 1952672 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4023. Min Act: -0.1700
Data Index: 8562279 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.4023. Min Act: -0.1700
Data Index: 970688 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9648. Min Range: -6.9648
Max Act: 6.3711. Min Act: -0.1700
Data Index: 8039777 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19