Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5050 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1348. Min Range: -4.1348
Max Act: 4.1348. Min Act: -0.1700
Data Index: 302817 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.9159. Min Act: -0.1700
Data Index: 5021540 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.8690. Min Act: -0.1700
Data Index: 3084512 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.8065. Min Act: -0.1700
Data Index: 6754340 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7909. Min Act: -0.1700
Data Index: 5028378 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7909. Min Act: -0.1700
Data Index: 3727946 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7752. Min Act: -0.1700
Data Index: 5557725 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7283. Min Act: -0.1700
Data Index: 503057 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7283. Min Act: -0.1700
Data Index: 6435956 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.7283. Min Act: -0.1700
Data Index: 4144797 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6970. Min Act: -0.1700
Data Index: 247154 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6814. Min Act: -0.1700
Data Index: 3696056 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6814. Min Act: -0.1700
Data Index: 6158439 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6501. Min Act: -0.1700
Data Index: 5324886 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6657. Min Act: -0.1700
Data Index: 3969118 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6344. Min Act: -0.1700
Data Index: 7204121 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6501. Min Act: -0.1700
Data Index: 4550773 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6501. Min Act: -0.1700
Data Index: 2107071 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6344. Min Act: -0.1700
Data Index: 3011164 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1348. Min Range: -4.1348
Max Act: 3.6501. Min Act: -0.1700
Data Index: 4695910 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19