Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.9661. Min Act: -0.1700
Data Index: 5149040 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.8098. Min Act: -0.1700
Data Index: 7116561 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.4661. Min Act: -0.1700
Data Index: 6342573 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.4348. Min Act: -0.1700
Data Index: 1332356 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.4348. Min Act: -0.1700
Data Index: 3977740 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.4036. Min Act: -0.1700
Data Index: 7451114 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.3723. Min Act: -0.1700
Data Index: 2066793 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.3411. Min Act: -0.1700
Data Index: 819941 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.3411. Min Act: -0.1700
Data Index: 3790042 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.3411. Min Act: -0.1700
Data Index: 3242720 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.3411. Min Act: -0.1700
Data Index: 7171410 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2786. Min Act: -0.1700
Data Index: 4692104 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2786. Min Act: -0.1700
Data Index: 5229458 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2473. Min Act: -0.1700
Data Index: 3138822 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2473. Min Act: -0.1700
Data Index: 8769763 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2473. Min Act: -0.1700
Data Index: 7844914 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2161. Min Act: -0.1700
Data Index: 8345923 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2161. Min Act: -0.1700
Data Index: 7875038 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.2161. Min Act: -0.1700
Data Index: 6650772 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9661. Min Range: -6.9661
Max Act: 6.1848. Min Act: -0.1700
Data Index: 446515 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19