Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1133. Min Range: -7.1133
Max Act: 7.1133. Min Act: -0.1700
Data Index: 8442477 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1133. Min Range: -7.1133
Max Act: 7.0508. Min Act: -0.1700
Data Index: 3752489 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.9570. Min Act: -0.1700
Data Index: 8787865 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8945. Min Act: -0.1700
Data Index: 8555880 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.9258. Min Act: -0.1700
Data Index: 792663 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.9258. Min Act: -0.1700
Data Index: 1584704 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.9258. Min Act: -0.1700
Data Index: 6674598 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8945. Min Act: -0.1700
Data Index: 5952882 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8633. Min Act: -0.1700
Data Index: 453472 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8320. Min Act: -0.1700
Data Index: 4460356 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8320. Min Act: -0.1700
Data Index: 7873419 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8320. Min Act: -0.1700
Data Index: 7141613 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8320. Min Act: -0.1700
Data Index: 5630211 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8802888 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8008. Min Act: -0.1700
Data Index: 134889 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8320. Min Act: -0.1700
Data Index: 3425818 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.8008. Min Act: -0.1700
Data Index: 3161101 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.7695. Min Act: -0.1699
Data Index: 7646575 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5473052 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1133. Min Range: -7.1133
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5769747 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19