Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2413 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0507. Min Range: -6.0507
Max Act: 6.0507. Min Act: -0.1700
Data Index: 3836294 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.4257. Min Act: -0.1700
Data Index: 3031759 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.3944. Min Act: -0.1700
Data Index: 744958 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.3319. Min Act: -0.1700
Data Index: 3921346 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.3007. Min Act: -0.1700
Data Index: 3416771 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2382. Min Act: -0.1700
Data Index: 8670515 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2382. Min Act: -0.1700
Data Index: 6581969 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2382. Min Act: -0.1700
Data Index: 8092128 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2069. Min Act: -0.1700
Data Index: 2879590 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2069. Min Act: -0.1700
Data Index: 5183181 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2069. Min Act: -0.1700
Data Index: 8681308 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2069. Min Act: -0.1700
Data Index: 4808324 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2382. Min Act: -0.1700
Data Index: 3938867 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.2069. Min Act: -0.1700
Data Index: 8663945 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1757. Min Act: -0.1700
Data Index: 4577496 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1757. Min Act: -0.1700
Data Index: 4710424 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1444. Min Act: -0.1700
Data Index: 3405589 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1444. Min Act: -0.1700
Data Index: 914726 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1444. Min Act: -0.1700
Data Index: 3618069 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0507. Min Range: -6.0507
Max Act: 5.1444. Min Act: -0.1700
Data Index: 5466458 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19