Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0720. Min Range: -4.0720
Max Act: 4.0720. Min Act: -0.1700
Data Index: 4706554 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0720. Min Range: -4.0720
Max Act: 4.0095. Min Act: -0.1700
Data Index: 5240696 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.9157. Min Act: -0.1700
Data Index: 8178531 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8844. Min Act: -0.1700
Data Index: 3021301 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8844. Min Act: -0.1700
Data Index: 1557441 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.9157. Min Act: -0.1700
Data Index: 2535780 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8531. Min Act: -0.1700
Data Index: 5645195 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8531. Min Act: -0.1700
Data Index: 1280478 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8531. Min Act: -0.1700
Data Index: 2093537 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8531. Min Act: -0.1700
Data Index: 3881362 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.8062. Min Act: -0.1700
Data Index: 6736086 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7906. Min Act: -0.1700
Data Index: 1759239 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7906. Min Act: -0.1700
Data Index: 5588782 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7750. Min Act: -0.1700
Data Index: 8137472 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7750. Min Act: -0.1700
Data Index: 4664588 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7750. Min Act: -0.1700
Data Index: 4545822 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7593. Min Act: -0.1700
Data Index: 1987232 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7593. Min Act: -0.1700
Data Index: 3299892 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7280. Min Act: -0.1700
Data Index: 2064680 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0720. Min Range: -4.0720
Max Act: 3.7280. Min Act: -0.1700
Data Index: 5019450 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19