Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.8280. Min Act: -0.1700
Data Index: 8557409 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.7342. Min Act: -0.1700
Data Index: 4524630 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.7342. Min Act: -0.1700
Data Index: 8808253 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.6403. Min Act: -0.1700
Data Index: 8466124 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.6090. Min Act: -0.1700
Data Index: 18326 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5777. Min Act: -0.1700
Data Index: 5466442 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.6090. Min Act: -0.1700
Data Index: 3591026 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5777. Min Act: -0.1700
Data Index: 3146919 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5777. Min Act: -0.1700
Data Index: 3736385 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5464. Min Act: -0.1700
Data Index: 2604333 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5464. Min Act: -0.1700
Data Index: 2873260 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5151. Min Act: -0.1700
Data Index: 2144887 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4546147 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5151. Min Act: -0.1700
Data Index: 7889098 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5151. Min Act: -0.1700
Data Index: 1347304 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5151. Min Act: -0.1700
Data Index: 7084548 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.5151. Min Act: -0.1700
Data Index: 5848807 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.4838. Min Act: -0.1700
Data Index: 8017695 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.4838. Min Act: -0.1700
Data Index: 4702446 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8280. Min Range: -3.8280
Max Act: 3.4838. Min Act: -0.1700
Data Index: 4731840 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19