Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5328 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.9728. Min Act: -0.1700
Data Index: 8181855 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.9416. Min Act: -0.1700
Data Index: 8438046 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.7853. Min Act: -0.1700
Data Index: 7685922 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.7853. Min Act: -0.1699
Data Index: 3640803 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.7228. Min Act: -0.1700
Data Index: 3221481 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.7228. Min Act: -0.1699
Data Index: 6646533 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6916. Min Act: -0.1700
Data Index: 4761473 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6916. Min Act: -0.1700
Data Index: 2295299 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6916. Min Act: -0.1700
Data Index: 1283630 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.7228. Min Act: -0.1700
Data Index: 6277065 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6916. Min Act: -0.1700
Data Index: 6020474 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6603. Min Act: -0.1700
Data Index: 462678 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6603. Min Act: -0.1700
Data Index: 545778 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6603. Min Act: -0.1700
Data Index: 1116214 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6291. Min Act: -0.1700
Data Index: 2082704 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6291. Min Act: -0.1700
Data Index: 8013483 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6291. Min Act: -0.1698
Data Index: 4789225 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.6291. Min Act: -0.1700
Data Index: 4603354 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.5978. Min Act: -0.1700
Data Index: 1250205 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9728. Min Range: -5.9728
Max Act: 5.5666. Min Act: -0.1700
Data Index: 2670622 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19