Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3648. Min Range: -5.3648
Max Act: 5.3648. Min Act: -0.1700
Data Index: 8538327 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3648. Min Range: -5.3648
Max Act: 5.3336. Min Act: -0.1700
Data Index: 8538316 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3648. Min Range: -5.3648
Max Act: 5.3336. Min Act: -0.1700
Data Index: 348354 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3648. Min Range: -5.3648
Max Act: 5.3023. Min Act: -0.1700
Data Index: 348337 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.9273. Min Act: -0.1700
Data Index: 772264 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.8648. Min Act: -0.1700
Data Index: 7540721 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.8336. Min Act: -0.1700
Data Index: 772262 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.8023. Min Act: -0.1700
Data Index: 474301 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7711. Min Act: -0.1700
Data Index: 3940413 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7398. Min Act: -0.1700
Data Index: 3037020 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7086. Min Act: -0.1700
Data Index: 8133888 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7086. Min Act: -0.1700
Data Index: 5977589 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7086. Min Act: -0.1700
Data Index: 5644366 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.7086. Min Act: -0.1700
Data Index: 2154368 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6773. Min Act: -0.1700
Data Index: 4534287 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6773. Min Act: -0.1700
Data Index: 2690458 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6461. Min Act: -0.1700
Data Index: 4534282 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6461. Min Act: -0.1700
Data Index: 3812734 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6461. Min Act: -0.1700
Data Index: 6960519 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3648. Min Range: -5.3648
Max Act: 4.6461. Min Act: -0.1700
Data Index: 3752276 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19