Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.2632. Min Act: -0.1700
Data Index: 2440364 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.2632. Min Act: -0.1700
Data Index: 5530173 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.2007. Min Act: -0.1700
Data Index: 1876741 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.0757. Min Act: -0.1700
Data Index: 7577606 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.0132. Min Act: -0.1700
Data Index: 3994672 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2632. Min Range: -8.2632
Max Act: 8.0132. Min Act: -0.1700
Data Index: 8532334 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.9507. Min Act: -0.1700
Data Index: 4766681 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.8882. Min Act: -0.1700
Data Index: 7294727 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.8882. Min Act: -0.1700
Data Index: 7121806 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.8882. Min Act: -0.1700
Data Index: 1410075 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.8257. Min Act: -0.1700
Data Index: 4644154 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.8257. Min Act: -0.1700
Data Index: 5957461 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 6784312 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 2649576 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 8204538 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 1577491 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 7622725 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 879507 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 3631986 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2632. Min Range: -8.2632
Max Act: 7.7632. Min Act: -0.1700
Data Index: 2983823 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19