Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.3510. Min Act: -0.1700
Data Index: 1835623 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.2260. Min Act: -0.1700
Data Index: 8681451 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.2260. Min Act: -0.1700
Data Index: 5771980 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.2572. Min Act: -0.1700
Data Index: 3910108 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.2260. Min Act: -0.1700
Data Index: 2528936 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1947. Min Act: -0.1700
Data Index: 4876239 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1635. Min Act: -0.1700
Data Index: 4775140 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1322. Min Act: -0.1700
Data Index: 4911779 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 5177936 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1322. Min Act: -0.1700
Data Index: 6713088 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1322. Min Act: -0.1700
Data Index: 6929716 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 3174793 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1322. Min Act: -0.1700
Data Index: 8217025 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1322. Min Act: -0.1700
Data Index: 4813159 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 7190999 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 469131 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 8441557 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 4014303 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 1171706 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3510. Min Range: -6.3510
Max Act: 6.1010. Min Act: -0.1700
Data Index: 276560 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19