Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.1474. Min Act: -0.1700
Data Index: 8058430 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.1161. Min Act: -0.1700
Data Index: 1581843 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.1161. Min Act: -0.1700
Data Index: 4646134 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0536. Min Act: -0.1700
Data Index: 8118835 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0224. Min Act: -0.1700
Data Index: 8358074 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1474. Min Range: -4.1474
Max Act: 4.0224. Min Act: -0.1700
Data Index: 2642471 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9911. Min Act: -0.1700
Data Index: 6428693 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9911. Min Act: -0.1700
Data Index: 7709774 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9598. Min Act: -0.1700
Data Index: 7789771 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3255787 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9598. Min Act: -0.1700
Data Index: 2823752 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8973. Min Act: -0.1700
Data Index: 1727528 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9129. Min Act: -0.1700
Data Index: 7883450 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9129. Min Act: -0.1700
Data Index: 5088760 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9129. Min Act: -0.1700
Data Index: 1799322 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.9129. Min Act: -0.1700
Data Index: 6212337 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8973. Min Act: -0.1700
Data Index: 139686 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8817. Min Act: -0.1700
Data Index: 5958830 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8660. Min Act: -0.1700
Data Index: 2145525 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1474. Min Range: -4.1474
Max Act: 3.8660. Min Act: -0.1700
Data Index: 2396972 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19