Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.9092. Min Act: -0.1700
Data Index: 2947543 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.4717. Min Act: -0.1700
Data Index: 1851517 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.4405. Min Act: -0.1700
Data Index: 7873442 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.4092. Min Act: -0.1700
Data Index: 6073276 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.3467. Min Act: -0.1700
Data Index: 4156482 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.3155. Min Act: -0.1700
Data Index: 7780413 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.2842. Min Act: -0.1700
Data Index: 5153794 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.2530. Min Act: -0.1700
Data Index: 6501018 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3062704 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1905. Min Act: -0.1700
Data Index: 8663615 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1905. Min Act: -0.1700
Data Index: 5594676 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 4062323 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 5053639 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 3277875 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 7841279 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1592. Min Act: -0.1700
Data Index: 925894 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1280. Min Act: -0.1700
Data Index: 4707224 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1280. Min Act: -0.1700
Data Index: 491180 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1280. Min Act: -0.1700
Data Index: 1488645 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9092. Min Range: -5.9092
Max Act: 5.1280. Min Act: -0.1700
Data Index: 5841878 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19