Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5698 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0808. Min Range: -9.0808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 1204138 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0808. Min Range: -9.0808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 1204127 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.9558. Min Act: -0.1700
Data Index: 1204145 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.9558. Min Act: -0.1700
Data Index: 1466816 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.8933. Min Act: -0.1700
Data Index: 8422666 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.8933. Min Act: -0.1699
Data Index: 322545 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.8308. Min Act: -0.1700
Data Index: 2963161 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 5413139 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7683. Min Act: -0.1700
Data Index: 6200462 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.8308. Min Act: -0.1699
Data Index: 590645 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 508657 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 4355689 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 5652024 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 4354174 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 155232 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1699
Data Index: 4214890 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 2516519 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 58515 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1700
Data Index: 6202905 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0808. Min Range: -9.0808
Max Act: 8.7058. Min Act: -0.1699
Data Index: 2943957 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19