Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3113 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.5831. Min Act: -0.1700
Data Index: 4027955 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.4893. Min Act: -0.1700
Data Index: 7608784 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3956. Min Act: -0.1700
Data Index: 2297346 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.4268. Min Act: -0.1700
Data Index: 5105435 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3956. Min Act: -0.1700
Data Index: 6384550 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3331. Min Act: -0.1700
Data Index: 8058188 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3331. Min Act: -0.1700
Data Index: 449289 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3331. Min Act: -0.1700
Data Index: 1011173 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3331. Min Act: -0.1700
Data Index: 8450456 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 1911897 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.3018. Min Act: -0.1700
Data Index: 4735600 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8404973 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 1105821 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2706. Min Act: -0.1700
Data Index: 210693 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2081. Min Act: -0.1700
Data Index: 2196073 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2393. Min Act: -0.1700
Data Index: 5642153 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2393. Min Act: -0.1700
Data Index: 4963955 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2393. Min Act: -0.1700
Data Index: 3425162 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.2081. Min Act: -0.1700
Data Index: 570528 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5831. Min Range: -5.5831
Max Act: 5.1768. Min Act: -0.1700
Data Index: 5197150 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19