Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1298 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0399. Min Range: -5.0399
Max Act: 5.0399. Min Act: -0.1700
Data Index: 7307355 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0399. Min Range: -5.0399
Max Act: 5.0086. Min Act: -0.1700
Data Index: 845782 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.9149. Min Act: -0.1700
Data Index: 3356914 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8524. Min Act: -0.1700
Data Index: 1227820 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.6649. Min Act: -0.1700
Data Index: 6433389 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.6024. Min Act: -0.1700
Data Index: 3485638 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.6024. Min Act: -0.1700
Data Index: 5511638 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.5711. Min Act: -0.1700
Data Index: 416055 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.5086. Min Act: -0.1700
Data Index: 2624489 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4774. Min Act: -0.1700
Data Index: 4218681 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.5086. Min Act: -0.1700
Data Index: 52012 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.5086. Min Act: -0.1700
Data Index: 4762586 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4461. Min Act: -0.1700
Data Index: 7569538 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1162399 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4461. Min Act: -0.1700
Data Index: 8185591 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4149. Min Act: -0.1700
Data Index: 7483671 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1660768 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4461. Min Act: -0.1700
Data Index: 3062144 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4149. Min Act: -0.1700
Data Index: 6201680 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.4149. Min Act: -0.1700
Data Index: 694343 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19