Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.6113. Min Act: -0.1675
Data Index: 278787 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.5488. Min Act: -0.1668
Data Index: 1196682 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4550. Min Act: -0.1682
Data Index: 6213731 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4238. Min Act: -0.1626
Data Index: 856308 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4550. Min Act: -0.1698
Data Index: 2553257 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4550. Min Act: -0.1697
Data Index: 7222826 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.4238. Min Act: -0.1697
Data Index: 7122677 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3925. Min Act: -0.1678
Data Index: 8580663 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3925. Min Act: -0.1698
Data Index: 7378432 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3925. Min Act: -0.1698
Data Index: 7316155 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3613. Min Act: -0.1391
Data Index: 4429893 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3613. Min Act: -0.1579
Data Index: 5069761 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3300. Min Act: -0.1657
Data Index: 4234605 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3300. Min Act: -0.1700
Data Index: 5806665 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.3300. Min Act: -0.1693
Data Index: 2411815 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2675. Min Act: -0.1699
Data Index: 7349766 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2988. Min Act: -0.1678
Data Index: 92892 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2675. Min Act: -0.1435
Data Index: 5392699 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2988. Min Act: -0.1614
Data Index: 521746 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6113. Min Range: -6.6113
Max Act: 6.2988. Min Act: -0.1689
Data Index: 4640413 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19