Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.6479. Min Act: -0.1700
Data Index: 3889581 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.6158. Min Act: -0.1700
Data Index: 5117853 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5997. Min Act: -0.1700
Data Index: 7589315 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5675. Min Act: -0.1700
Data Index: 548122 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5513. Min Act: -0.1700
Data Index: 3137422 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5513. Min Act: -0.1700
Data Index: 7462552 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5352. Min Act: -0.1700
Data Index: 5481838 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5190. Min Act: -0.1700
Data Index: 4173702 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5028. Min Act: -0.1700
Data Index: 4689050 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5190. Min Act: -0.1700
Data Index: 377098 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5190. Min Act: -0.1700
Data Index: 3301079 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5190. Min Act: -0.1700
Data Index: 6552470 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5190. Min Act: -0.1700
Data Index: 8730656 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5028. Min Act: -0.1700
Data Index: 7650801 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.5028. Min Act: -0.1700
Data Index: 3026408 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.4541. Min Act: -0.1700
Data Index: 5909946 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.4704. Min Act: -0.1700
Data Index: 8744690 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.4541. Min Act: -0.1700
Data Index: 5410703 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.4379. Min Act: -0.1700
Data Index: 7719021 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6479. Min Range: -2.6479
Max Act: 2.4541. Min Act: -0.1700
Data Index: 553657 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19