Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1934 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.2176. Min Act: -0.1700
Data Index: 2322987 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.2176. Min Act: -0.1700
Data Index: 4802797 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.1238. Min Act: -0.1700
Data Index: 8369462 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0925. Min Act: -0.1700
Data Index: 2614256 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0925. Min Act: -0.1700
Data Index: 5840679 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0300. Min Act: -0.1700
Data Index: 8792177 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0613. Min Act: -0.1700
Data Index: 7823069 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0300. Min Act: -0.1700
Data Index: 1340894 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2176. Min Range: -4.2176
Max Act: 4.0300. Min Act: -0.1700
Data Index: 7260414 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9988. Min Act: -0.1700
Data Index: 7623464 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9988. Min Act: -0.1700
Data Index: 7862900 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3779589 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9988. Min Act: -0.1700
Data Index: 1751778 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4360486 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 876968 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4871072 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 4608930 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3322662 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 5958809 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2176. Min Range: -4.2176
Max Act: 3.9675. Min Act: -0.1700
Data Index: 106077 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19