Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.9279. Min Act: -0.1700
Data Index: 8071575 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.8029. Min Act: -0.1700
Data Index: 3632201 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.8029. Min Act: -0.1700
Data Index: 92804 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7717. Min Act: -0.1700
Data Index: 1634399 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7404. Min Act: -0.1700
Data Index: 5983329 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7404. Min Act: -0.1700
Data Index: 6640162 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7091. Min Act: -0.1700
Data Index: 5113180 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7091. Min Act: -0.1700
Data Index: 7231192 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 6059125 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 7471594 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 1733317 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 8498527 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6927907 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 5970434 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 2140657 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 1270632 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5102710 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5799342 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 1924934 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5301106 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19