Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.5515. Min Act: -0.1700
Data Index: 2635400 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.5515. Min Act: -0.1700
Data Index: 8099275 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.5030. Min Act: -0.1700
Data Index: 4686205 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.5030. Min Act: -0.1700
Data Index: 8718 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.4543. Min Act: -0.1700
Data Index: 5101564 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.4380. Min Act: -0.1700
Data Index: 5614179 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.4217. Min Act: -0.1700
Data Index: 1580931 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.4217. Min Act: -0.1700
Data Index: 6706838 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3728. Min Act: -0.1700
Data Index: 4257155 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3728. Min Act: -0.1700
Data Index: 54390 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3564. Min Act: -0.1700
Data Index: 8279373 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3564. Min Act: -0.1700
Data Index: 6217804 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3728. Min Act: -0.1700
Data Index: 6217801 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3564. Min Act: -0.1700
Data Index: 1709861 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3564. Min Act: -0.1700
Data Index: 4732311 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3400. Min Act: -0.1700
Data Index: 5344799 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3564. Min Act: -0.1700
Data Index: 6902882 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3072. Min Act: -0.1700
Data Index: 6658367 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3400. Min Act: -0.1700
Data Index: 6184801 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5515. Min Range: -2.5515
Max Act: 2.3236. Min Act: -0.1700
Data Index: 6184802 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19