Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2338 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.3361. Min Act: -0.1700
Data Index: 5454694 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.3049. Min Act: -0.1700
Data Index: 5648607 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.2736. Min Act: -0.1700
Data Index: 237595 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.2424. Min Act: -0.1700
Data Index: 8737538 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1798. Min Act: -0.1700
Data Index: 113130 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.2424. Min Act: -0.1700
Data Index: 3424698 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.2111. Min Act: -0.1700
Data Index: 6915365 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1798. Min Act: -0.1700
Data Index: 4969276 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1798. Min Act: -0.1700
Data Index: 1883006 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1173. Min Act: -0.1700
Data Index: 8536839 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1798. Min Act: -0.1700
Data Index: 4515636 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.1173. Min Act: -0.1700
Data Index: 8132172 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0861. Min Act: -0.1700
Data Index: 7112294 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0861. Min Act: -0.1700
Data Index: 4296725 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0548. Min Act: -0.1700
Data Index: 161476 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0861. Min Act: -0.1700
Data Index: 5328363 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0548. Min Act: -0.1700
Data Index: 5387063 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0548. Min Act: -0.1700
Data Index: 2194067 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0548. Min Act: -0.1700
Data Index: 7272835 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3361. Min Range: -4.3361
Max Act: 4.0548. Min Act: -0.1700
Data Index: 8243413 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19