Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.7417. Min Act: -0.1700
Data Index: 3902707 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.4917. Min Act: -0.1700
Data Index: 356725 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.4292. Min Act: -0.1700
Data Index: 4495186 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3980. Min Act: -0.1700
Data Index: 6634745 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3980. Min Act: -0.1700
Data Index: 3977581 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.4292. Min Act: -0.1700
Data Index: 6768865 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3042. Min Act: -0.1700
Data Index: 2555162 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3042. Min Act: -0.1700
Data Index: 3560336 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3042. Min Act: -0.1700
Data Index: 1611190 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.3042. Min Act: -0.1700
Data Index: 587433 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 1676372 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2730. Min Act: -0.1700
Data Index: 6380846 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 5457069 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2105. Min Act: -0.1700
Data Index: 3079573 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 7470836 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 2461468 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 4602918 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 4573770 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2417. Min Act: -0.1700
Data Index: 1975733 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7417. Min Range: -4.7417
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1725156 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19