Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4341 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0808. Min Range: -8.0808
Max Act: 8.0808. Min Act: -0.1700
Data Index: 798871 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.9558. Min Act: -0.1700
Data Index: 7515869 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.8933. Min Act: -0.1700
Data Index: 3768347 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.8308. Min Act: -0.1700
Data Index: 917236 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.8308. Min Act: -0.1700
Data Index: 3730516 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.7683. Min Act: -0.1700
Data Index: 1140166 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.7683. Min Act: -0.1700
Data Index: 8072755 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.7683. Min Act: -0.1700
Data Index: 8497158 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.7058. Min Act: -0.1700
Data Index: 4857783 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.6433. Min Act: -0.1700
Data Index: 3730515 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5808. Min Act: -0.1700
Data Index: 5446620 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.6433. Min Act: -0.1700
Data Index: 4180798 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5808. Min Act: -0.1700
Data Index: 2955078 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5183. Min Act: -0.1700
Data Index: 2165922 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5808. Min Act: -0.1700
Data Index: 8124043 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5183. Min Act: -0.1700
Data Index: 71665 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5183. Min Act: -0.1700
Data Index: 799567 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.5183. Min Act: -0.1700
Data Index: 5495827 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.4558. Min Act: -0.1700
Data Index: 444702 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0808. Min Range: -8.0808
Max Act: 7.4558. Min Act: -0.1700
Data Index: 1675641 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19