Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.7569. Min Act: -0.1700
Data Index: 1002055 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6630. Min Act: -0.1700
Data Index: 1811400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6630. Min Act: -0.1700
Data Index: 3087812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6630. Min Act: -0.1700
Data Index: 2703604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6630. Min Act: -0.1700
Data Index: 4060423 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6317. Min Act: -0.1700
Data Index: 4578173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6317. Min Act: -0.1700
Data Index: 5752809 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6317. Min Act: -0.1700
Data Index: 8146329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6317. Min Act: -0.1700
Data Index: 352253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6317. Min Act: -0.1700
Data Index: 3214716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 8049752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 4468141 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 1875591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 8783765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 7658381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 5550531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 6668641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.5691. Min Act: -0.1700
Data Index: 4656526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.6004. Min Act: -0.1700
Data Index: 5538592 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7569. Min Range: -3.7569
Max Act: 3.5691. Min Act: -0.1700
Data Index: 5587895 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19