Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0799. Min Range: -5.0799
Max Act: 5.0799. Min Act: -0.1700
Data Index: 8261827 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9862. Min Act: -0.1700
Data Index: 4026031 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9549. Min Act: -0.1700
Data Index: 6848602 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9549. Min Act: -0.1700
Data Index: 497666 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9549. Min Act: -0.1700
Data Index: 4698968 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9862. Min Act: -0.1700
Data Index: 250849 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.9237. Min Act: -0.1700
Data Index: 2560445 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8924. Min Act: -0.1700
Data Index: 735166 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8924. Min Act: -0.1700
Data Index: 2241163 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8924. Min Act: -0.1700
Data Index: 1475674 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8924. Min Act: -0.1700
Data Index: 3722834 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8612. Min Act: -0.1700
Data Index: 3288276 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7987. Min Act: -0.1700
Data Index: 5683140 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8299. Min Act: -0.1700
Data Index: 2055104 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.8299. Min Act: -0.1700
Data Index: 4459630 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7987. Min Act: -0.1700
Data Index: 86059 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7987. Min Act: -0.1700
Data Index: 5459703 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7674. Min Act: -0.1700
Data Index: 7729358 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7674. Min Act: -0.1700
Data Index: 6044646 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0799. Min Range: -5.0799
Max Act: 4.7987. Min Act: -0.1700
Data Index: 6156386 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19