Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.2512. Min Act: -0.1700
Data Index: 4698211 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5859885 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.1887. Min Act: -0.1700
Data Index: 5031358 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.1575. Min Act: -0.1700
Data Index: 7402791 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0950. Min Act: -0.1700
Data Index: 2877807 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0637. Min Act: -0.1700
Data Index: 1502104 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0637. Min Act: -0.1700
Data Index: 3439240 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0325. Min Act: -0.1700
Data Index: 5801226 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0325. Min Act: -0.1700
Data Index: 4261475 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0012. Min Act: -0.1700
Data Index: 2088211 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0012. Min Act: -0.1700
Data Index: 7729225 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0012. Min Act: -0.1700
Data Index: 924117 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9700. Min Act: -0.1700
Data Index: 5848361 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2541919 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9700. Min Act: -0.1700
Data Index: 1235423 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2512. Min Range: -5.2512
Max Act: 5.0012. Min Act: -0.1700
Data Index: 7572079 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9387. Min Act: -0.1700
Data Index: 5710072 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9387. Min Act: -0.1700
Data Index: 5349033 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9387. Min Act: -0.1700
Data Index: 2150640 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2512. Min Range: -5.2512
Max Act: 4.9075. Min Act: -0.1700
Data Index: 2861438 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19