Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4821. Min Act: -0.1700
Data Index: 6587201 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.4509. Min Act: -0.1700
Data Index: 6774774 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.3258. Min Act: -0.1700
Data Index: 2890576 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.2633. Min Act: -0.1700
Data Index: 3358725 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.1071. Min Act: -0.1700
Data Index: 4993065 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.0446. Min Act: -0.1700
Data Index: 7232485 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.0446. Min Act: -0.1700
Data Index: 2423955 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.0133. Min Act: -0.1700
Data Index: 2072975 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.0133. Min Act: -0.1700
Data Index: 5797065 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4821. Min Range: -4.4821
Max Act: 4.0446. Min Act: -0.1700
Data Index: 1651446 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9820. Min Act: -0.1700
Data Index: 3560467 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9820. Min Act: -0.1700
Data Index: 7388718 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9820. Min Act: -0.1700
Data Index: 6360731 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 3378790 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 3373258 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2835954 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 4895940 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 1228506 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9195. Min Act: -0.1700
Data Index: 1452873 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4821. Min Range: -4.4821
Max Act: 3.9508. Min Act: -0.1700
Data Index: 3560449 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19