Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2395 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.4774. Min Act: -0.1700
Data Index: 1859896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.4461. Min Act: -0.1700
Data Index: 7312421 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.4149. Min Act: -0.1700
Data Index: 3479678 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.4149. Min Act: -0.1700
Data Index: 2356628 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3836. Min Act: -0.1700
Data Index: 6336098 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3836. Min Act: -0.1700
Data Index: 4268033 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7150208 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3524. Min Act: -0.1700
Data Index: 4424997 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3524. Min Act: -0.1700
Data Index: 6036262 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1243933 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3836. Min Act: -0.1700
Data Index: 1302849 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3836. Min Act: -0.1700
Data Index: 7637188 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3524. Min Act: -0.1700
Data Index: 2372866 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3211. Min Act: -0.1700
Data Index: 63402 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3211. Min Act: -0.1700
Data Index: 6722821 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.2899. Min Act: -0.1700
Data Index: 7703383 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3211. Min Act: -0.1700
Data Index: 1443039 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.2899. Min Act: -0.1700
Data Index: 5671492 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3211. Min Act: -0.1700
Data Index: 1776408 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4774. Min Range: -4.4774
Max Act: 4.3211. Min Act: -0.1700
Data Index: 4386490 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19