Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.7127. Min Act: -0.1700
Data Index: 5720194 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.5564. Min Act: -0.1700
Data Index: 1438379 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.4002. Min Act: -0.1700
Data Index: 6654860 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.3689. Min Act: -0.1700
Data Index: 1230280 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.3377. Min Act: -0.1700
Data Index: 6572246 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.3064. Min Act: -0.1700
Data Index: 505552 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2752. Min Act: -0.1700
Data Index: 6574881 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2752. Min Act: -0.1700
Data Index: 5151922 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2752. Min Act: -0.1700
Data Index: 8822389 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2439. Min Act: -0.1700
Data Index: 6635190 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2439. Min Act: -0.1700
Data Index: 1506055 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2439. Min Act: -0.1700
Data Index: 2526260 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2127. Min Act: -0.1700
Data Index: 5308909 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.2127. Min Act: -0.1700
Data Index: 5045163 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 5759501 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 2098140 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 2221617 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 94460 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 2098141 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7127. Min Range: -5.7127
Max Act: 5.1814. Min Act: -0.1700
Data Index: 1263072 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19