Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2449. Min Range: -5.2449
Max Act: 5.2449. Min Act: -0.1700
Data Index: 4107743 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2449. Min Range: -5.2449
Max Act: 5.2136. Min Act: -0.1700
Data Index: 4642147 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2449. Min Range: -5.2449
Max Act: 5.1511. Min Act: -0.1700
Data Index: 3848213 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2449. Min Range: -5.2449
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7278115 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2449. Min Range: -5.2449
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2457635 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9636. Min Act: -0.1700
Data Index: 6972659 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9636. Min Act: -0.1700
Data Index: 6280880 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9011. Min Act: -0.1700
Data Index: 6972657 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9011. Min Act: -0.1700
Data Index: 2492540 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9011. Min Act: -0.1700
Data Index: 7852729 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.9011. Min Act: -0.1700
Data Index: 1381592 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.8386. Min Act: -0.1700
Data Index: 2674289 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.8074. Min Act: -0.1700
Data Index: 2772940 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7761. Min Act: -0.1700
Data Index: 4839843 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7449. Min Act: -0.1700
Data Index: 4788184 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7761. Min Act: -0.1700
Data Index: 738858 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7449. Min Act: -0.1700
Data Index: 7939740 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7136. Min Act: -0.1700
Data Index: 765876 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.7136. Min Act: -0.1700
Data Index: 6816525 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2449. Min Range: -5.2449
Max Act: 4.6824. Min Act: -0.1700
Data Index: 3123416 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19