Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.1817. Min Act: -0.1700
Data Index: 8356229 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.0880. Min Act: -0.1700
Data Index: 749995 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.0880. Min Act: -0.1700
Data Index: 1403197 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.0567. Min Act: -0.1700
Data Index: 1468019 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.0880. Min Act: -0.1700
Data Index: 3142053 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1817. Min Range: -7.1817
Max Act: 7.0255. Min Act: -0.1700
Data Index: 1468056 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.9942. Min Act: -0.1700
Data Index: 5504300 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.9630. Min Act: -0.1700
Data Index: 2200024 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8692. Min Act: -0.1700
Data Index: 4248883 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8380. Min Act: -0.1700
Data Index: 8647289 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8380. Min Act: -0.1700
Data Index: 1824935 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8380. Min Act: -0.1700
Data Index: 1805647 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8067. Min Act: -0.1700
Data Index: 5147072 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.8067. Min Act: -0.1700
Data Index: 6064225 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.7755. Min Act: -0.1700
Data Index: 4731920 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.7442. Min Act: -0.1700
Data Index: 2640261 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.7442. Min Act: -0.1700
Data Index: 5508226 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.7442. Min Act: -0.1700
Data Index: 1202390 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.7130. Min Act: -0.1700
Data Index: 5508218 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1817. Min Range: -7.1817
Max Act: 6.6505. Min Act: -0.1700
Data Index: 1067886 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19