Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9741. Min Act: -0.1700
Data Index: 4264527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0054. Min Range: -4.0054
Max Act: 4.0054. Min Act: -0.1700
Data Index: 7656594 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9741. Min Act: -0.1699
Data Index: 4183116 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9741. Min Act: -0.1700
Data Index: 5583322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 26777 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 367294 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 1180446 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 3996071 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 2678619 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 5716839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 964358 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 2381114 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 3689034 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 3574659 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 3567593 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 305422 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 5484501 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 5040434 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 481134 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9429. Min Act: -0.1700
Data Index: 3256454 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19