Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0920. Min Range: -7.0920
Max Act: 7.0920. Min Act: -0.1700
Data Index: 507505 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0920. Min Range: -7.0920
Max Act: 7.0295. Min Act: -0.1700
Data Index: 356791 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.9358. Min Act: -0.1700
Data Index: 1934407 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.8733. Min Act: -0.1700
Data Index: 5317983 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.8733. Min Act: -0.1700
Data Index: 5129453 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.8420. Min Act: -0.1700
Data Index: 6388413 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.8108. Min Act: -0.1700
Data Index: 448496 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.8108. Min Act: -0.1700
Data Index: 3547946 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7795. Min Act: -0.1700
Data Index: 8050897 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 6211562 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 6152578 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 5274763 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 3148658 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7483. Min Act: -0.1700
Data Index: 2110025 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6858. Min Act: -0.1700
Data Index: 4619235 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.7170. Min Act: -0.1700
Data Index: 206127 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6858. Min Act: -0.1700
Data Index: 830220 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 2389470 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6690645 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0920. Min Range: -7.0920
Max Act: 6.6545. Min Act: -0.1700
Data Index: 1525369 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19