Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.6625. Min Act: -0.1700
Data Index: 7764064 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.5375. Min Act: -0.1700
Data Index: 3939557 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.4750. Min Act: -0.1700
Data Index: 3582234 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.4125. Min Act: -0.1700
Data Index: 1437122 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.4125. Min Act: -0.1700
Data Index: 4707583 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.3500. Min Act: -0.1700
Data Index: 5399370 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2875. Min Act: -0.1700
Data Index: 7061788 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2875. Min Act: -0.1700
Data Index: 8773639 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2875. Min Act: -0.1700
Data Index: 1017236 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2875. Min Act: -0.1700
Data Index: 2649735 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2250. Min Act: -0.1700
Data Index: 2430311 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.2250. Min Act: -0.1700
Data Index: 643737 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1625. Min Act: -0.1700
Data Index: 1901200 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1625. Min Act: -0.1700
Data Index: 3732089 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1625. Min Act: -0.1700
Data Index: 3183711 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1000. Min Act: -0.1700
Data Index: 4019342 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1000. Min Act: -0.1700
Data Index: 642089 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1000. Min Act: -0.1700
Data Index: 5010166 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1625. Min Act: -0.1700
Data Index: 976910 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6625. Min Range: -9.6625
Max Act: 9.1000. Min Act: -0.1700
Data Index: 1075178 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19