Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2073 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0801. Min Range: -8.0801
Max Act: 8.0801. Min Act: -0.1700
Data Index: 10663 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0801. Min Range: -8.0801
Max Act: 8.0801. Min Act: -0.1700
Data Index: 4120882 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 8501340 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 5851519 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 1330020 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 108879 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 8587849 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.8301. Min Act: -0.1700
Data Index: 3764924 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 3861875 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 7941407 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 8292629 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7676. Min Act: -0.1700
Data Index: 6184487 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.7051. Min Act: -0.1700
Data Index: 2018222 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 4048846 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 901330 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 7016707 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 2235676 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.6426. Min Act: -0.1700
Data Index: 8569203 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.5801. Min Act: -0.1700
Data Index: 4432944 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0801. Min Range: -8.0801
Max Act: 7.5801. Min Act: -0.1700
Data Index: 1627271 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19