Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.7630. Min Act: -0.1700
Data Index: 8289172 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.7630. Min Act: -0.1700
Data Index: 1551146 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.7004. Min Act: -0.1700
Data Index: 1210267 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6691. Min Act: -0.1700
Data Index: 7846768 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6691. Min Act: -0.1700
Data Index: 2251279 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6535. Min Act: -0.1700
Data Index: 5134599 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6535. Min Act: -0.1700
Data Index: 7454324 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6378. Min Act: -0.1700
Data Index: 6801257 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6378. Min Act: -0.1700
Data Index: 1321085 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6378. Min Act: -0.1700
Data Index: 6301639 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6222. Min Act: -0.1700
Data Index: 5786187 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6065. Min Act: -0.1700
Data Index: 6949993 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5909. Min Act: -0.1700
Data Index: 6509512 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.6065. Min Act: -0.1700
Data Index: 4938689 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5752. Min Act: -0.1700
Data Index: 6348451 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5752. Min Act: -0.1700
Data Index: 7793810 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5596. Min Act: -0.1700
Data Index: 3506723 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5439. Min Act: -0.1700
Data Index: 681711 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5596. Min Act: -0.1700
Data Index: 898394 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7630. Min Range: -3.7630
Max Act: 3.5439. Min Act: -0.1700
Data Index: 1397614 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19