Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6306 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6099. Min Range: -5.6099
Max Act: 5.6099. Min Act: -0.1700
Data Index: 3381224 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6099. Min Range: -5.6099
Max Act: 5.2974. Min Act: -0.1700
Data Index: 7508190 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6099. Min Range: -5.6099
Max Act: 5.0787. Min Act: -0.1700
Data Index: 667036 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6099. Min Range: -5.6099
Max Act: 5.0162. Min Act: -0.1700
Data Index: 2977641 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6099. Min Range: -5.6099
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5233144 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9537. Min Act: -0.1700
Data Index: 2092809 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9537. Min Act: -0.1700
Data Index: 7442443 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9849. Min Act: -0.1700
Data Index: 2609772 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4641530 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 8723121 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 1638432 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 1849191 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 8593064 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 3715249 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 8146620 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 69216 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 8828631 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 2426161 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 2882628 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6099. Min Range: -5.6099
Max Act: 4.8912. Min Act: -0.1700
Data Index: 4580271 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19