Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.2466. Min Act: -0.1700
Data Index: 5024420 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.2153. Min Act: -0.1700
Data Index: 1536339 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.2153. Min Act: -0.1700
Data Index: 4730077 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 4519773 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1841. Min Act: -0.1700
Data Index: 5743718 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1528. Min Act: -0.1700
Data Index: 2377060 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1216. Min Act: -0.1700
Data Index: 4569351 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1216. Min Act: -0.1700
Data Index: 4327856 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1216. Min Act: -0.1700
Data Index: 628283 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.1216. Min Act: -0.1700
Data Index: 2735696 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0903. Min Act: -0.1700
Data Index: 4792776 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0903. Min Act: -0.1700
Data Index: 7790478 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0591. Min Act: -0.1700
Data Index: 5104522 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0591. Min Act: -0.1700
Data Index: 5408408 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0591. Min Act: -0.1700
Data Index: 1559190 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0591. Min Act: -0.1700
Data Index: 7323743 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0278. Min Act: -0.1700
Data Index: 6058678 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0278. Min Act: -0.1700
Data Index: 583213 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0278. Min Act: -0.1700
Data Index: 4239023 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2466. Min Range: -5.2466
Max Act: 5.0591. Min Act: -0.1700
Data Index: 5521700 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19