Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6168 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2627. Min Range: -6.2627
Max Act: 6.2627. Min Act: -0.1700
Data Index: 4668192 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2627. Min Range: -6.2627
Max Act: 6.2315. Min Act: -0.1700
Data Index: 2812000 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2627. Min Range: -6.2627
Max Act: 6.2002. Min Act: -0.1700
Data Index: 1785182 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2627. Min Range: -6.2627
Max Act: 6.0440. Min Act: -0.1700
Data Index: 6327965 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.9815. Min Act: -0.1700
Data Index: 1450398 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.9502. Min Act: -0.1700
Data Index: 301753 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.8877. Min Act: -0.1700
Data Index: 4983717 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.8565. Min Act: -0.1700
Data Index: 8468290 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4075945 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.8252. Min Act: -0.1700
Data Index: 4305393 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7940. Min Act: -0.1700
Data Index: 5640848 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7627. Min Act: -0.1700
Data Index: 4010292 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7627. Min Act: -0.1700
Data Index: 7881906 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7627. Min Act: -0.1700
Data Index: 8640295 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7940. Min Act: -0.1700
Data Index: 3900379 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7627. Min Act: -0.1700
Data Index: 6931545 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7315. Min Act: -0.1700
Data Index: 6434620 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7002. Min Act: -0.1700
Data Index: 3606880 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7002. Min Act: -0.1700
Data Index: 4875791 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2627. Min Range: -6.2627
Max Act: 5.7002. Min Act: -0.1700
Data Index: 285677 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19