Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2971 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1511. Min Range: -4.1511
Max Act: 4.1511. Min Act: -0.1700
Data Index: 7580121 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1511. Min Range: -4.1511
Max Act: 4.1511. Min Act: -0.1700
Data Index: 4521114 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1511. Min Range: -4.1511
Max Act: 4.0574. Min Act: -0.1700
Data Index: 8066488 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9948. Min Act: -0.1700
Data Index: 6929098 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9636. Min Act: -0.1700
Data Index: 8272377 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9323. Min Act: -0.1700
Data Index: 3093411 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9323. Min Act: -0.1700
Data Index: 2993229 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9323. Min Act: -0.1700
Data Index: 69132 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9167. Min Act: -0.1700
Data Index: 4653692 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9323. Min Act: -0.1700
Data Index: 8328498 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9011. Min Act: -0.1700
Data Index: 4860553 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9011. Min Act: -0.1700
Data Index: 2576493 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.9011. Min Act: -0.1700
Data Index: 5435629 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8542. Min Act: -0.1700
Data Index: 7124034 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8542. Min Act: -0.1700
Data Index: 26522 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8698. Min Act: -0.1700
Data Index: 3309815 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8542. Min Act: -0.1700
Data Index: 1817906 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8385. Min Act: -0.1700
Data Index: 3540513 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8385. Min Act: -0.1700
Data Index: 1288883 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1511. Min Range: -4.1511
Max Act: 3.8385. Min Act: -0.1700
Data Index: 3905873 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19