Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2730. Min Range: -6.2730
Max Act: 6.2730. Min Act: -0.1700
Data Index: 8081227 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2730. Min Range: -6.2730
Max Act: 6.2417. Min Act: -0.1700
Data Index: 5964048 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2730. Min Range: -6.2730
Max Act: 6.0855. Min Act: -0.1700
Data Index: 145356 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2730. Min Range: -6.2730
Max Act: 6.0230. Min Act: -0.1700
Data Index: 4707844 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9917. Min Act: -0.1700
Data Index: 165493 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9605. Min Act: -0.1700
Data Index: 4525076 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9605. Min Act: -0.1700
Data Index: 8540378 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9292. Min Act: -0.1700
Data Index: 165503 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9292. Min Act: -0.1700
Data Index: 589514 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9292. Min Act: -0.1700
Data Index: 731656 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8980. Min Act: -0.1700
Data Index: 4992071 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.9292. Min Act: -0.1700
Data Index: 2605761 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8667. Min Act: -0.1700
Data Index: 5593056 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8667. Min Act: -0.1700
Data Index: 299701 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8667. Min Act: -0.1700
Data Index: 2612066 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1349132 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8042. Min Act: -0.1700
Data Index: 5861517 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8355. Min Act: -0.1700
Data Index: 2786003 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8355. Min Act: -0.1700
Data Index: 3164543 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2730. Min Range: -6.2730
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1203525 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19