Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.9645. Min Act: -0.1700
Data Index: 6518019 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8708. Min Act: -0.1700
Data Index: 7045232 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8708. Min Act: -0.1700
Data Index: 3439113 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8395. Min Act: -0.1700
Data Index: 6623838 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.8083. Min Act: -0.1700
Data Index: 1924513 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7770. Min Act: -0.1700
Data Index: 2378156 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7458. Min Act: -0.1700
Data Index: 150341 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7145. Min Act: -0.1700
Data Index: 6435755 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.7145. Min Act: -0.1700
Data Index: 3294015 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6833. Min Act: -0.1700
Data Index: 7592174 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6833. Min Act: -0.1700
Data Index: 6346173 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6833. Min Act: -0.1700
Data Index: 2339437 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5895. Min Act: -0.1700
Data Index: 8052240 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6208. Min Act: -0.1700
Data Index: 5057142 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6208. Min Act: -0.1700
Data Index: 8091188 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6208. Min Act: -0.1700
Data Index: 6575957 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5895. Min Act: -0.1700
Data Index: 7509077 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5895. Min Act: -0.1700
Data Index: 5175118 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.6208. Min Act: -0.1700
Data Index: 2550069 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9645. Min Range: -4.9645
Max Act: 4.5895. Min Act: -0.1700
Data Index: 8049896 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19