Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8425. Min Range: -6.8425
Max Act: 6.8425. Min Act: -0.1700
Data Index: 8211705 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8425. Min Range: -6.8425
Max Act: 6.2175. Min Act: -0.1700
Data Index: 1176660 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8425. Min Range: -6.8425
Max Act: 6.2175. Min Act: -0.1700
Data Index: 5944167 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8425. Min Range: -6.8425
Max Act: 6.1862. Min Act: -0.1700
Data Index: 6888421 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8425. Min Range: -6.8425
Max Act: 6.0612. Min Act: -0.1700
Data Index: 2307593 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4326239 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3691681 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3243163 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6864918 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8737. Min Act: -0.1700
Data Index: 1203638 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8737. Min Act: -0.1700
Data Index: 6458418 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8737. Min Act: -0.1700
Data Index: 6633703 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8737. Min Act: -0.1700
Data Index: 1651760 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8425. Min Act: -0.1700
Data Index: 6075259 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8425. Min Act: -0.1700
Data Index: 3565847 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8112. Min Act: -0.1700
Data Index: 1546699 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8425. Min Act: -0.1700
Data Index: 5189793 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8425. Min Act: -0.1700
Data Index: 3520740 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8112. Min Act: -0.1700
Data Index: 2656198 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8425. Min Range: -6.8425
Max Act: 5.8112. Min Act: -0.1700
Data Index: 2820927 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19