Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4856. Min Act: -0.1700
Data Index: 8510025 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.4856. Min Act: -0.1700
Data Index: 8151933 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3295914 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 1321321 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3941168 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3606. Min Act: -0.1700
Data Index: 8439413 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3294. Min Act: -0.1700
Data Index: 4518363 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.3294. Min Act: -0.1700
Data Index: 2897449 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2669. Min Act: -0.1700
Data Index: 2279953 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2981. Min Act: -0.1700
Data Index: 5157749 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2669. Min Act: -0.1700
Data Index: 2689754 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2669. Min Act: -0.1700
Data Index: 6597677 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2669. Min Act: -0.1700
Data Index: 4183531 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2356. Min Act: -0.1700
Data Index: 1426685 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 6218666 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 478195 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 6946854 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 8795592 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 3986863 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4856. Min Range: -5.4856
Max Act: 5.2044. Min Act: -0.1700
Data Index: 2812614 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19