Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0458. Min Range: -3.0458
Max Act: 3.0458. Min Act: -0.1700
Data Index: 3275383 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8717. Min Act: -0.1700
Data Index: 2140679 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8717. Min Act: -0.1700
Data Index: 2948867 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8558. Min Act: -0.1700
Data Index: 2224486 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8240. Min Act: -0.1700
Data Index: 2722069 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8399. Min Act: -0.1700
Data Index: 6259836 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8399. Min Act: -0.1700
Data Index: 6590710 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8558. Min Act: -0.1700
Data Index: 7967107 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8399. Min Act: -0.1700
Data Index: 5577598 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8240. Min Act: -0.1700
Data Index: 7755088 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8081. Min Act: -0.1700
Data Index: 1030607 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.8081. Min Act: -0.1700
Data Index: 3831147 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7922. Min Act: -0.1700
Data Index: 5786514 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7763. Min Act: -0.1700
Data Index: 7205734 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7763. Min Act: -0.1700
Data Index: 4910396 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7763. Min Act: -0.1700
Data Index: 4665835 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7763. Min Act: -0.1700
Data Index: 6340544 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7603. Min Act: -0.1700
Data Index: 2173625 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7603. Min Act: -0.1700
Data Index: 1231744 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0458. Min Range: -3.0458
Max Act: 2.7603. Min Act: -0.1700
Data Index: 93943 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19