Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1338 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.4487. Min Act: -0.1700
Data Index: 1222826 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.3549. Min Act: -0.1700
Data Index: 4130843 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.1362. Min Act: -0.1700
Data Index: 434540 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.1674. Min Act: -0.1700
Data Index: 2907646 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.1362. Min Act: -0.1700
Data Index: 7625706 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.1049. Min Act: -0.1700
Data Index: 4265456 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.0424. Min Act: -0.1700
Data Index: 5582842 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.0424. Min Act: -0.1700
Data Index: 1092512 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.0112. Min Act: -0.1700
Data Index: 1332354 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4487. Min Range: -7.4487
Max Act: 7.0424. Min Act: -0.1700
Data Index: 3400105 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.9799. Min Act: -0.1700
Data Index: 3412535 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.9799. Min Act: -0.1700
Data Index: 7643268 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.9487. Min Act: -0.1700
Data Index: 5448966 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.9487. Min Act: -0.1700
Data Index: 1917632 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.9174. Min Act: -0.1700
Data Index: 3283101 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 8664130 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 3610708 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 4614519 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.8862. Min Act: -0.1700
Data Index: 1200453 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4487. Min Range: -7.4487
Max Act: 6.8549. Min Act: -0.1700
Data Index: 7308192 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19