Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.5327. Min Act: -0.1700
Data Index: 6065826 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.3452. Min Act: -0.1700
Data Index: 6281196 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.2827. Min Act: -0.1700
Data Index: 7316124 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.2202. Min Act: -0.1700
Data Index: 5389 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.1577. Min Act: -0.1700
Data Index: 7723478 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.0327. Min Act: -0.1700
Data Index: 6994652 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5327. Min Range: -8.5327
Max Act: 8.0327. Min Act: -0.1700
Data Index: 4100709 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.9702. Min Act: -0.1700
Data Index: 1326734 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.9702. Min Act: -0.1700
Data Index: 8420093 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.9077. Min Act: -0.1700
Data Index: 2878950 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.8452. Min Act: -0.1700
Data Index: 6951800 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.8452. Min Act: -0.1700
Data Index: 6421906 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.8139. Min Act: -0.1700
Data Index: 486546 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.8139. Min Act: -0.1700
Data Index: 5325543 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7827. Min Act: -0.1700
Data Index: 5184368 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7827. Min Act: -0.1700
Data Index: 4735824 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7827. Min Act: -0.1700
Data Index: 7096896 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7827. Min Act: -0.1700
Data Index: 2596741 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7514. Min Act: -0.1700
Data Index: 8238080 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5327. Min Range: -8.5327
Max Act: 7.7827. Min Act: -0.1700
Data Index: 258376 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19