Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.5898. Min Act: -0.1700
Data Index: 329900 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.4335. Min Act: -0.1700
Data Index: 8090490 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.2773. Min Act: -0.1700
Data Index: 870749 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.2460. Min Act: -0.1700
Data Index: 8801082 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.2460. Min Act: -0.1700
Data Index: 6021538 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.1835. Min Act: -0.1700
Data Index: 1527589 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.1523. Min Act: -0.1700
Data Index: 2372303 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.1523. Min Act: -0.1700
Data Index: 680409 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.1210. Min Act: -0.1700
Data Index: 2518526 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0898. Min Act: -0.1700
Data Index: 4977689 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0898. Min Act: -0.1700
Data Index: 2917260 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.1210. Min Act: -0.1700
Data Index: 600079 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0898. Min Act: -0.1700
Data Index: 5493809 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0585. Min Act: -0.1700
Data Index: 7334130 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0585. Min Act: -0.1700
Data Index: 4362689 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0272. Min Act: -0.1700
Data Index: 5214185 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5898. Min Range: -4.5898
Max Act: 4.0272. Min Act: -0.1700
Data Index: 8536034 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5898. Min Range: -4.5898
Max Act: 3.9960. Min Act: -0.1700
Data Index: 4810825 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5898. Min Range: -4.5898
Max Act: 3.9960. Min Act: -0.1700
Data Index: 4269637 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5898. Min Range: -4.5898
Max Act: 3.9647. Min Act: -0.1700
Data Index: 6275350 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19