Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.8279. Min Act: -0.1700
Data Index: 7488572 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.5779. Min Act: -0.1700
Data Index: 5225369 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6402856 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2967. Min Act: -0.1700
Data Index: 661822 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2654. Min Act: -0.1700
Data Index: 6485779 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2654. Min Act: -0.1700
Data Index: 7272575 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 3728 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2342. Min Act: -0.1700
Data Index: 912395 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.2029. Min Act: -0.1700
Data Index: 6770936 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1958222 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.1404. Min Act: -0.1700
Data Index: 4124916 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.1092. Min Act: -0.1700
Data Index: 4421520 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.1717. Min Act: -0.1700
Data Index: 3157675 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.1404. Min Act: -0.1700
Data Index: 6485774 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0779. Min Act: -0.1700
Data Index: 7464979 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0779. Min Act: -0.1700
Data Index: 5733609 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0779. Min Act: -0.1700
Data Index: 2669843 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0154. Min Act: -0.1700
Data Index: 2145071 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0467. Min Act: -0.1700
Data Index: 6347444 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8279. Min Range: -5.8279
Max Act: 5.0154. Min Act: -0.1700
Data Index: 195207 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19