Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5854 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.2446. Min Act: -0.1700
Data Index: 1007657 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.2446. Min Act: -0.1700
Data Index: 4787641 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.1821. Min Act: -0.1700
Data Index: 1289513 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0884. Min Act: -0.1700
Data Index: 3788154 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.1196. Min Act: -0.1700
Data Index: 3239745 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0884. Min Act: -0.1700
Data Index: 995142 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0571. Min Act: -0.1700
Data Index: 4986319 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0884. Min Act: -0.1700
Data Index: 6208845 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0571. Min Act: -0.1700
Data Index: 3143 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0884. Min Act: -0.1700
Data Index: 6911782 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0571. Min Act: -0.1700
Data Index: 6990755 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0571. Min Act: -0.1700
Data Index: 4778790 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 1895858 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 1953169 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 1350462 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 3867160 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0571. Min Act: -0.1700
Data Index: 3421871 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 1500918 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5997752 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2446. Min Range: -5.2446
Max Act: 5.0259. Min Act: -0.1700
Data Index: 5514539 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19