Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.2696. Min Act: -0.1700
Data Index: 8756788 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.2344. Min Act: -0.1686
Data Index: 3787524 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1815. Min Act: -0.1658
Data Index: 6508362 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.2167. Min Act: -0.1693
Data Index: 6880458 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1815. Min Act: -0.0784
Data Index: 8101192 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1639. Min Act: -0.1203
Data Index: 6350500 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1113. Min Act: -0.1174
Data Index: 8607287 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1113. Min Act: -0.1690
Data Index: 6880457 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.1288. Min Act: -0.1466
Data Index: 4743747 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0588. Min Act: -0.1476
Data Index: 6103834 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0413. Min Act: -0.1645
Data Index: 596523 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0413. Min Act: -0.1700
Data Index: 2097114 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0239. Min Act: -0.1507
Data Index: 955750 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0065. Min Act: -0.1135
Data Index: 4832127 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2696. Min Range: -1.2696
Max Act: 1.0065. Min Act: -0.1654
Data Index: 6848005 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2696. Min Range: -1.2696
Max Act: 0.9719. Min Act: -0.1587
Data Index: 2092352 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2696. Min Range: -1.2696
Max Act: 0.9892. Min Act: -0.0990
Data Index: 6092800 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2696. Min Range: -1.2696
Max Act: 0.9892. Min Act: -0.1695
Data Index: 6161115 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2696. Min Range: -1.2696
Max Act: 0.9719. Min Act: -0.1692
Data Index: 1265506 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2696. Min Range: -1.2696
Max Act: 0.9719. Min Act: -0.1698
Data Index: 3384030 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19