Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5099 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.3676. Min Act: -0.1700
Data Index: 5175177 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.1176. Min Act: -0.1700
Data Index: 7888769 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.0864. Min Act: -0.1700
Data Index: 8429652 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3676. Min Range: -7.3676
Max Act: 7.0864. Min Act: -0.1700
Data Index: 356130 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9926. Min Act: -0.1700
Data Index: 3781204 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9926. Min Act: -0.1700
Data Index: 1733772 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9926. Min Act: -0.1700
Data Index: 148973 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9614. Min Act: -0.1700
Data Index: 2681247 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.9301. Min Act: -0.1700
Data Index: 7870591 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8989. Min Act: -0.1700
Data Index: 2715200 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8989. Min Act: -0.1700
Data Index: 3829716 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8676. Min Act: -0.1700
Data Index: 7719904 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 3546844 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 5747491 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 2345470 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 6475689 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8051. Min Act: -0.1700
Data Index: 2318547 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8051. Min Act: -0.1700
Data Index: 5155874 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.8364. Min Act: -0.1700
Data Index: 2894760 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3676. Min Range: -7.3676
Max Act: 6.7739. Min Act: -0.1700
Data Index: 4862093 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19