Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 864 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.8356. Min Act: -0.1700
Data Index: 3909430 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.8669. Min Act: -0.1700
Data Index: 2388933 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.8356. Min Act: -0.1700
Data Index: 971950 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.8043. Min Act: -0.1700
Data Index: 2743332 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.7731. Min Act: -0.1700
Data Index: 869931 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.7105. Min Act: -0.1700
Data Index: 333123 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.7105. Min Act: -0.1700
Data Index: 4113502 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.7105. Min Act: -0.1700
Data Index: 3691868 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.7105. Min Act: -0.1700
Data Index: 7998769 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6792. Min Act: -0.1700
Data Index: 1560800 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6479. Min Act: -0.1700
Data Index: 2037352 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6479. Min Act: -0.1700
Data Index: 5016846 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6323. Min Act: -0.1700
Data Index: 2111330 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6323. Min Act: -0.1700
Data Index: 2101395 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6166. Min Act: -0.1700
Data Index: 2034207 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6166. Min Act: -0.1700
Data Index: 6436200 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6010. Min Act: -0.1700
Data Index: 123270 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6010. Min Act: -0.1700
Data Index: 225878 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6166. Min Act: -0.1700
Data Index: 6296710 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8669. Min Range: -3.8669
Max Act: 3.6010. Min Act: -0.1700
Data Index: 4506229 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19