Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0964. Min Range: -6.0964
Max Act: 6.0964. Min Act: -0.1700
Data Index: 1381378 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.9402. Min Act: -0.1700
Data Index: 7763638 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.8777. Min Act: -0.1700
Data Index: 1007751 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.8777. Min Act: -0.1700
Data Index: 6242571 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.8464. Min Act: -0.1700
Data Index: 3499057 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.7839. Min Act: -0.1700
Data Index: 6056858 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.7527. Min Act: -0.1700
Data Index: 2531557 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 123034 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 931846 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.7214. Min Act: -0.1700
Data Index: 2230019 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.7214. Min Act: -0.1700
Data Index: 93820 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 5968858 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4980355 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 8562204 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6902. Min Act: -0.1700
Data Index: 501269 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6277. Min Act: -0.1700
Data Index: 771034 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6589. Min Act: -0.1700
Data Index: 5914408 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6277. Min Act: -0.1700
Data Index: 7664105 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6589. Min Act: -0.1700
Data Index: 370017 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0964. Min Range: -6.0964
Max Act: 5.6277. Min Act: -0.1700
Data Index: 2350138 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19