Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6399 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.8151. Min Act: -0.1700
Data Index: 4376554 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.8151. Min Act: -0.1700
Data Index: 3210386 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.7526. Min Act: -0.1700
Data Index: 5492383 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.7214. Min Act: -0.1700
Data Index: 2253261 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.7526. Min Act: -0.1700
Data Index: 5054717 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.6589. Min Act: -0.1700
Data Index: 4833100 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.6589. Min Act: -0.1700
Data Index: 4098554 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.6589. Min Act: -0.1700
Data Index: 6829287 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5964. Min Act: -0.1700
Data Index: 1877631 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.6276. Min Act: -0.1700
Data Index: 6351771 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.6276. Min Act: -0.1700
Data Index: 7365895 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5964. Min Act: -0.1700
Data Index: 937218 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5651. Min Act: -0.1700
Data Index: 2353669 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5964. Min Act: -0.1700
Data Index: 3132422 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5339. Min Act: -0.1700
Data Index: 4559545 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5651. Min Act: -0.1700
Data Index: 247023 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5651. Min Act: -0.1700
Data Index: 1213527 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5339. Min Act: -0.1700
Data Index: 1475314 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5651. Min Act: -0.1700
Data Index: 366102 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8151. Min Range: -4.8151
Max Act: 4.5339. Min Act: -0.1700
Data Index: 5332024 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19