Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.1817. Min Act: -0.1700
Data Index: 7927544 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.1484. Min Act: -0.1700
Data Index: 5147951 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.1317. Min Act: -0.1700
Data Index: 4366662 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.1150. Min Act: -0.1700
Data Index: 1914945 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0815. Min Act: -0.1700
Data Index: 7284060 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0815. Min Act: -0.1700
Data Index: 5923858 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0647. Min Act: -0.1700
Data Index: 5128689 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0311. Min Act: -0.1700
Data Index: 6844406 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 7223179 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 3894680 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 7034115 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 6636330 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 5757237 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1817. Min Range: -2.1817
Max Act: 2.0142. Min Act: -0.1700
Data Index: 2846002 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9973. Min Act: -0.1700
Data Index: 3701827 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9973. Min Act: -0.1700
Data Index: 1995422 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9973. Min Act: -0.1700
Data Index: 1281756 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9973. Min Act: -0.1700
Data Index: 7113682 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9973. Min Act: -0.1700
Data Index: 4347052 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1817. Min Range: -2.1817
Max Act: 1.9804. Min Act: -0.1700
Data Index: 4085941 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19