Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4753 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3939. Min Range: -8.3939
Max Act: 8.3939. Min Act: -0.1700
Data Index: 6126246 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3939. Min Range: -8.3939
Max Act: 7.7689. Min Act: -0.1700
Data Index: 8785719 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3939. Min Range: -8.3939
Max Act: 7.5189. Min Act: -0.1700
Data Index: 1908844 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3939. Min Range: -8.3939
Max Act: 7.4564. Min Act: -0.1700
Data Index: 8312618 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3939. Min Range: -8.3939
Max Act: 7.2064. Min Act: -0.1700
Data Index: 6418841 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3939. Min Range: -8.3939
Max Act: 7.0189. Min Act: -0.1700
Data Index: 520692 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.9564. Min Act: -0.1700
Data Index: 6439655 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.9252. Min Act: -0.1700
Data Index: 8794517 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.9252. Min Act: -0.1700
Data Index: 6782440 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 6026853 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 668558 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.9252. Min Act: -0.1700
Data Index: 5230069 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 8083901 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 1649270 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 2901164 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 102154 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 1510599 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8314. Min Act: -0.1700
Data Index: 2129683 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 7000685 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3939. Min Range: -8.3939
Max Act: 6.8314. Min Act: -0.1700
Data Index: 1525371 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19