Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2400 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.2874. Min Act: -0.1700
Data Index: 8209097 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.1624. Min Act: -0.1700
Data Index: 350539 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.1312. Min Act: -0.1700
Data Index: 7451252 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0374. Min Act: -0.1700
Data Index: 8190078 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0687. Min Act: -0.1700
Data Index: 4804949 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 2873141 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 2382685 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 1349026 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 2832810 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0374. Min Act: -0.1700
Data Index: 8627592 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 3420376 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 1117738 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2874. Min Range: -4.2874
Max Act: 4.0061. Min Act: -0.1700
Data Index: 1677210 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 1458025 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 1901195 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 8735122 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9436. Min Act: -0.1700
Data Index: 2519727 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 3290107 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 4162689 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2874. Min Range: -4.2874
Max Act: 3.9749. Min Act: -0.1700
Data Index: 5501486 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19