Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2994 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.4454. Min Act: -0.1700
Data Index: 2319904 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.3517. Min Act: -0.1700
Data Index: 7513803 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.2892. Min Act: -0.1700
Data Index: 1046300 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.2892. Min Act: -0.1700
Data Index: 4109149 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.2579. Min Act: -0.1700
Data Index: 8130693 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.2267. Min Act: -0.1700
Data Index: 6510213 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.2267. Min Act: -0.1700
Data Index: 2638744 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1954. Min Act: -0.1700
Data Index: 6270542 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1642. Min Act: -0.1700
Data Index: 1844009 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1329. Min Act: -0.1700
Data Index: 4182735 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1642. Min Act: -0.1700
Data Index: 2508363 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1329. Min Act: -0.1700
Data Index: 1974981 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1329. Min Act: -0.1700
Data Index: 96070 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.1017. Min Act: -0.1700
Data Index: 5276813 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0704. Min Act: -0.1700
Data Index: 8072933 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0704. Min Act: -0.1700
Data Index: 2293783 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0704. Min Act: -0.1700
Data Index: 6401396 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0704. Min Act: -0.1700
Data Index: 6358439 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0392. Min Act: -0.1700
Data Index: 5194077 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4454. Min Range: -5.4454
Max Act: 5.0392. Min Act: -0.1700
Data Index: 4882419 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19