Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.8810. Min Act: -0.1700
Data Index: 8007716 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.9123. Min Act: -0.1700
Data Index: 5414744 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.8498. Min Act: -0.1700
Data Index: 2565157 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.8498. Min Act: -0.1700
Data Index: 8087122 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.7873. Min Act: -0.1700
Data Index: 1270983 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.7248. Min Act: -0.1700
Data Index: 3369165 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6935. Min Act: -0.1700
Data Index: 7825454 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6623. Min Act: -0.1700
Data Index: 4841877 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1202365 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6935. Min Act: -0.1700
Data Index: 1505778 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6623. Min Act: -0.1700
Data Index: 4608311 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6623. Min Act: -0.1700
Data Index: 7286903 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6310. Min Act: -0.1700
Data Index: 7409195 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6310. Min Act: -0.1700
Data Index: 4423252 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6310. Min Act: -0.1700
Data Index: 2312111 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6310. Min Act: -0.1700
Data Index: 4409008 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.6310. Min Act: -0.1700
Data Index: 3407658 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.5998. Min Act: -0.1700
Data Index: 1074107 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.5998. Min Act: -0.1700
Data Index: 583213 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9123. Min Range: -5.9123
Max Act: 5.5685. Min Act: -0.1700
Data Index: 2819836 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19