Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.9481. Min Act: -0.1700
Data Index: 1169230 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.9168. Min Act: -0.1700
Data Index: 8086713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 2304226 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 2861985 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 4782003 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 6423818 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 6652469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 6915349 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 7630037 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8856. Min Act: -0.1700
Data Index: 207116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 376692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1698
Data Index: 281417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8230. Min Act: -0.1700
Data Index: 486998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 226849 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 366040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 425625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 25504 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 313116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 448204 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9481. Min Range: -3.9481
Max Act: 3.8543. Min Act: -0.1700
Data Index: 405130 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19