Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5622 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0824. Min Act: -0.1700
Data Index: 4790243 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0355. Min Act: -0.1700
Data Index: 7349395 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0511. Min Act: -0.1700
Data Index: 6748778 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0511. Min Act: -0.1700
Data Index: 3566892 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0355. Min Act: -0.1700
Data Index: 3612878 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0199. Min Act: -0.1700
Data Index: 7692644 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0355. Min Act: -0.1700
Data Index: 7364367 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0355. Min Act: -0.1700
Data Index: 2819682 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0355. Min Act: -0.1700
Data Index: 1989496 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0199. Min Act: -0.1700
Data Index: 4896087 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 4842193 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 563912 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 4506604 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0199. Min Act: -0.1700
Data Index: 7261502 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9886. Min Act: -0.1700
Data Index: 8001843 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 4137845 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9886. Min Act: -0.1700
Data Index: 4684956 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 7128332 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0824. Min Range: -4.0824
Max Act: 4.0042. Min Act: -0.1700
Data Index: 3616539 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0824. Min Range: -4.0824
Max Act: 3.9730. Min Act: -0.1700
Data Index: 5695616 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19