Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2161. Min Range: -8.2161
Max Act: 8.2161. Min Act: -0.1700
Data Index: 5062415 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.5911. Min Act: -0.1700
Data Index: 7044042 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.5911. Min Act: -0.1700
Data Index: 3703465 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.4661. Min Act: -0.1700
Data Index: 3073959 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.4036. Min Act: -0.1700
Data Index: 3666475 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.4036. Min Act: -0.1700
Data Index: 7115405 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.4036. Min Act: -0.1700
Data Index: 7615875 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.3724. Min Act: -0.1700
Data Index: 7485235 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.3099. Min Act: -0.1700
Data Index: 740459 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.3099. Min Act: -0.1700
Data Index: 5180815 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.3099. Min Act: -0.1700
Data Index: 7711552 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.2474. Min Act: -0.1700
Data Index: 60275 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.2474. Min Act: -0.1700
Data Index: 7563859 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.2161. Min Act: -0.1700
Data Index: 5068253 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1849. Min Act: -0.1700
Data Index: 5840370 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1849. Min Act: -0.1700
Data Index: 5860901 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1849. Min Act: -0.1700
Data Index: 1865082 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1849. Min Act: -0.1700
Data Index: 5499404 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1224. Min Act: -0.1700
Data Index: 6752661 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2161. Min Range: -8.2161
Max Act: 7.1224. Min Act: -0.1700
Data Index: 3369127 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19