Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.7672. Min Act: -0.1700
Data Index: 5765487 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.7047. Min Act: -0.1700
Data Index: 116934 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.5485. Min Act: -0.1700
Data Index: 21616 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.3610. Min Act: -0.1700
Data Index: 7798266 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.3610. Min Act: -0.1700
Data Index: 4381607 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.2985. Min Act: -0.1700
Data Index: 4869832 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.2985. Min Act: -0.1700
Data Index: 1602997 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.2360. Min Act: -0.1700
Data Index: 1850181 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.2360. Min Act: -0.1700
Data Index: 3500674 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0797. Min Act: -0.1700
Data Index: 7618232 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.1110. Min Act: -0.1700
Data Index: 6337692 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0485. Min Act: -0.1700
Data Index: 318930 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0797. Min Act: -0.1700
Data Index: 6889057 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0172. Min Act: -0.1700
Data Index: 1386541 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0485. Min Act: -0.1700
Data Index: 1843333 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0172. Min Act: -0.1700
Data Index: 3708424 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0172. Min Act: -0.1700
Data Index: 2109519 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7672. Min Range: -7.7672
Max Act: 6.9860. Min Act: -0.1700
Data Index: 440597 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7672. Min Range: -7.7672
Max Act: 7.0172. Min Act: -0.1700
Data Index: 7152992 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7672. Min Range: -7.7672
Max Act: 6.9547. Min Act: -0.1700
Data Index: 447424 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19