Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4619 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.6200. Min Act: -0.1700
Data Index: 6865762 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4638. Min Act: -0.1700
Data Index: 169547 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4638. Min Act: -0.1700
Data Index: 8173068 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4638. Min Act: -0.1700
Data Index: 3450810 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4638. Min Act: -0.1700
Data Index: 2572688 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4638. Min Act: -0.1700
Data Index: 5717732 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4325. Min Act: -0.1700
Data Index: 5843746 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4013. Min Act: -0.1700
Data Index: 1783785 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.4013. Min Act: -0.1700
Data Index: 7910633 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 5838768 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 429030 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 3417003 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 1868020 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 5843747 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 325797 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3700. Min Act: -0.1700
Data Index: 2217487 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3388. Min Act: -0.1700
Data Index: 3951614 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3388. Min Act: -0.1700
Data Index: 4329948 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3388. Min Act: -0.1700
Data Index: 7654205 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6200. Min Range: -4.6200
Max Act: 4.3388. Min Act: -0.1700
Data Index: 7665312 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19