Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.5670. Min Act: -0.1700
Data Index: 6445334 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3795. Min Act: -0.1700
Data Index: 3073166 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3795. Min Act: -0.1700
Data Index: 3298261 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3795. Min Act: -0.1700
Data Index: 6086348 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3795. Min Act: -0.1700
Data Index: 4733182 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3482. Min Act: -0.1700
Data Index: 4518559 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4968290 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4973830 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 86330 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 8538261 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4127022 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4297898 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 3709740 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 4520299 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.3170. Min Act: -0.1700
Data Index: 6347342 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.2857. Min Act: -0.1700
Data Index: 4241293 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.2545. Min Act: -0.1700
Data Index: 2219917 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.2857. Min Act: -0.1700
Data Index: 4994656 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.2857. Min Act: -0.1700
Data Index: 5313533 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5670. Min Range: -5.5670
Max Act: 5.2857. Min Act: -0.1700
Data Index: 3490862 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19