Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6022 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.1658. Min Act: -0.1700
Data Index: 6195608 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.1033. Min Act: -0.1700
Data Index: 4546058 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2524024 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0720. Min Act: -0.1700
Data Index: 5525296 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0408. Min Act: -0.1700
Data Index: 2416547 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0720. Min Act: -0.1700
Data Index: 6057394 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0408. Min Act: -0.1700
Data Index: 1787452 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0408. Min Act: -0.1700
Data Index: 4568302 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 2313483 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 7482538 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 3052182 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 6553205 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 1296859 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1658. Min Range: -6.1658
Max Act: 6.0095. Min Act: -0.1700
Data Index: 22634 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9783. Min Act: -0.1700
Data Index: 6661354 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9783. Min Act: -0.1700
Data Index: 5226701 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9783. Min Act: -0.1700
Data Index: 6055914 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9783. Min Act: -0.1700
Data Index: 4291540 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9783. Min Act: -0.1700
Data Index: 2404605 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1658. Min Range: -6.1658
Max Act: 5.9470. Min Act: -0.1700
Data Index: 2719679 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19