Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.8383. Min Act: -0.1700
Data Index: 5595660 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.4946. Min Act: -0.1700
Data Index: 6292042 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.4008. Min Act: -0.1700
Data Index: 6677802 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.3071. Min Act: -0.1700
Data Index: 1281777 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2758. Min Act: -0.1700
Data Index: 8179860 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2758. Min Act: -0.1700
Data Index: 4076909 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2758. Min Act: -0.1700
Data Index: 1276140 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2446. Min Act: -0.1700
Data Index: 6020941 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2446. Min Act: -0.1700
Data Index: 1281776 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2446. Min Act: -0.1700
Data Index: 7656487 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2446. Min Act: -0.1700
Data Index: 3093401 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1821. Min Act: -0.1700
Data Index: 3053173 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.2133. Min Act: -0.1700
Data Index: 3472402 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1821. Min Act: -0.1700
Data Index: 4865879 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1821. Min Act: -0.1700
Data Index: 3583590 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 2852095 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 6509726 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 5880612 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 7043002 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8383. Min Range: -4.8383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 2660772 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19