Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1295 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.3577. Min Act: -0.1700
Data Index: 981123 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2952. Min Act: -0.1700
Data Index: 955028 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2639. Min Act: -0.1700
Data Index: 3318430 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2639. Min Act: -0.1700
Data Index: 8522693 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2327. Min Act: -0.1700
Data Index: 1112689 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2327. Min Act: -0.1700
Data Index: 2616647 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2327. Min Act: -0.1700
Data Index: 1311469 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2014. Min Act: -0.1700
Data Index: 47567 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.2014. Min Act: -0.1700
Data Index: 1271194 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1699
Data Index: 736952 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1693
Data Index: 937394 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1700
Data Index: 2114438 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3270659 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1700
Data Index: 8522692 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1389. Min Act: -0.1700
Data Index: 1903670 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1389. Min Act: -0.1700
Data Index: 4192395 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1389. Min Act: -0.1700
Data Index: 5615581 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3675765 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1389. Min Act: -0.1700
Data Index: 3479984 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3577. Min Range: -5.3577
Max Act: 5.1077. Min Act: -0.1700
Data Index: 4985296 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19