Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4631 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.3634. Min Act: -0.1700
Data Index: 5920984 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.2384. Min Act: -0.1700
Data Index: 4197835 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.2696. Min Act: -0.1700
Data Index: 5453032 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.2071. Min Act: -0.1700
Data Index: 3749348 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.2384. Min Act: -0.1700
Data Index: 2436827 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1446. Min Act: -0.1700
Data Index: 8727947 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1446. Min Act: -0.1700
Data Index: 553269 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0821. Min Act: -0.1700
Data Index: 7289168 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1134. Min Act: -0.1700
Data Index: 6806784 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.1134. Min Act: -0.1700
Data Index: 7893387 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0821. Min Act: -0.1700
Data Index: 1322384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0509. Min Act: -0.1700
Data Index: 7822972 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3634. Min Range: -6.3634
Max Act: 6.0509. Min Act: -0.1700
Data Index: 5841185 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9884. Min Act: -0.1700
Data Index: 1856316 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 7334955 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 1998123 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9571. Min Act: -0.1700
Data Index: 2292763 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9259. Min Act: -0.1700
Data Index: 7002251 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9259. Min Act: -0.1700
Data Index: 7108072 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3634. Min Range: -6.3634
Max Act: 5.9259. Min Act: -0.1700
Data Index: 2715416 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19