Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.4577. Min Act: -0.1700
Data Index: 8662676 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.4414. Min Act: -0.1700
Data Index: 6569082 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.4088. Min Act: -0.1700
Data Index: 301863 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.4251. Min Act: -0.1700
Data Index: 4405528 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.4088. Min Act: -0.1700
Data Index: 7190430 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3762. Min Act: -0.1700
Data Index: 5530677 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3598. Min Act: -0.1700
Data Index: 5270656 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3762. Min Act: -0.1700
Data Index: 1924533 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3434. Min Act: -0.1700
Data Index: 6688200 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3434. Min Act: -0.1700
Data Index: 8378294 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3434. Min Act: -0.1700
Data Index: 7190032 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1699
Data Index: 5113182 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3598. Min Act: -0.1700
Data Index: 8368026 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3434. Min Act: -0.1700
Data Index: 2749065 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1700
Data Index: 6294906 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1700
Data Index: 8368025 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1700
Data Index: 3907987 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1700
Data Index: 7377597 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3434. Min Act: -0.1700
Data Index: 2452001 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4577. Min Range: -2.4577
Max Act: 2.3270. Min Act: -0.1700
Data Index: 8674387 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19