Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.6836. Min Act: -0.1700
Data Index: 3904652 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.4649. Min Act: -0.1700
Data Index: 7997871 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.3399. Min Act: -0.1700
Data Index: 8054478 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.2461. Min Act: -0.1700
Data Index: 1247679 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.2461. Min Act: -0.1700
Data Index: 3418716 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.2149. Min Act: -0.1700
Data Index: 3472825 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.2149. Min Act: -0.1700
Data Index: 1567501 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.1836. Min Act: -0.1700
Data Index: 6999706 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.1524. Min Act: -0.1700
Data Index: 7866037 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.1524. Min Act: -0.1700
Data Index: 8740088 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.1211. Min Act: -0.1700
Data Index: 6263123 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6836. Min Range: -7.6836
Max Act: 7.0586. Min Act: -0.1700
Data Index: 1634512 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9961. Min Act: -0.1700
Data Index: 5573092 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6758640 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9649. Min Act: -0.1700
Data Index: 7300877 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9649. Min Act: -0.1700
Data Index: 19790 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9649. Min Act: -0.1700
Data Index: 5600981 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9024. Min Act: -0.1700
Data Index: 7101924 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9336. Min Act: -0.1700
Data Index: 6968407 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6836. Min Range: -7.6836
Max Act: 6.9336. Min Act: -0.1700
Data Index: 6507976 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19