Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3559 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2827. Min Range: -8.2827
Max Act: 8.2827. Min Act: -0.1700
Data Index: 6672977 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.8452. Min Act: -0.1700
Data Index: 2503855 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.7827. Min Act: -0.1700
Data Index: 3473548 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.7827. Min Act: -0.1700
Data Index: 5127567 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.7202. Min Act: -0.1700
Data Index: 5801090 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.7202. Min Act: -0.1700
Data Index: 7967326 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.7202. Min Act: -0.1700
Data Index: 245689 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5952. Min Act: -0.1700
Data Index: 3014416 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.6577. Min Act: -0.1700
Data Index: 5319269 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.6577. Min Act: -0.1700
Data Index: 2693312 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5952. Min Act: -0.1700
Data Index: 6548416 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5952. Min Act: -0.1700
Data Index: 4389035 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5952. Min Act: -0.1700
Data Index: 4288760 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5327. Min Act: -0.1700
Data Index: 20074 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5327. Min Act: -0.1700
Data Index: 6630367 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.5327. Min Act: -0.1700
Data Index: 3450051 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.4702. Min Act: -0.1700
Data Index: 3184259 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.4389. Min Act: -0.1700
Data Index: 100602 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.4702. Min Act: -0.1700
Data Index: 4419203 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2827. Min Range: -8.2827
Max Act: 7.4702. Min Act: -0.1700
Data Index: 1171738 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19