Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.5026. Min Act: -0.1700
Data Index: 7650147 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.3151. Min Act: -0.1700
Data Index: 3486844 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8744878 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6023374 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2213. Min Act: -0.1700
Data Index: 6134414 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 1575980 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 1464624 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 775560 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3470453 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1588. Min Act: -0.1700
Data Index: 2007624 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1588. Min Act: -0.1700
Data Index: 2071657 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1901. Min Act: -0.1700
Data Index: 362138 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0963. Min Act: -0.1700
Data Index: 8416032 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0963. Min Act: -0.1700
Data Index: 7192457 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 8027784 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 1917132 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 6749644 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0963. Min Act: -0.1700
Data Index: 1157273 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0963. Min Act: -0.1700
Data Index: 5088691 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 7256967 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19