Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.4743. Min Act: -0.1700
Data Index: 7805911 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.4418. Min Act: -0.1700
Data Index: 5372612 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.4092. Min Act: -0.1700
Data Index: 4456901 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 1236532 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 7735396 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 2220188 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 6117823 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 4456903 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3765. Min Act: -0.1700
Data Index: 7594921 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3438. Min Act: -0.1700
Data Index: 5372610 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3438. Min Act: -0.1700
Data Index: 3495829 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3438. Min Act: -0.1700
Data Index: 333468 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 599275 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 1068911 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 992471 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1698
Data Index: 4358077 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 6117242 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 6008716 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 3985470 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4743. Min Range: -2.4743
Max Act: 2.3274. Min Act: -0.1700
Data Index: 5494225 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19