Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.4764. Min Act: -0.1700
Data Index: 6573117 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1567362 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3826. Min Act: -0.1700
Data Index: 2024278 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3826. Min Act: -0.1700
Data Index: 1712716 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3514. Min Act: -0.1700
Data Index: 3364739 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3514. Min Act: -0.1700
Data Index: 2340338 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 1776362 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 7802368 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 8712583 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2889. Min Act: -0.1700
Data Index: 2481799 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 4972065 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 5799758 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.3201. Min Act: -0.1700
Data Index: 1035647 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2889. Min Act: -0.1700
Data Index: 6743709 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2889. Min Act: -0.1700
Data Index: 4518795 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2576. Min Act: -0.1700
Data Index: 4198974 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2576. Min Act: -0.1700
Data Index: 3062422 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2576. Min Act: -0.1700
Data Index: 6738380 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2576. Min Act: -0.1700
Data Index: 2923533 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4764. Min Range: -5.4764
Max Act: 5.2576. Min Act: -0.1700
Data Index: 159456 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19