Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5489 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.9018. Min Act: -0.1700
Data Index: 6798716 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.8393. Min Act: -0.1700
Data Index: 7066407 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.8393. Min Act: -0.1700
Data Index: 7569006 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.8080. Min Act: -0.1700
Data Index: 6467481 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.8393. Min Act: -0.1700
Data Index: 3813469 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7768. Min Act: -0.1700
Data Index: 6653512 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7768. Min Act: -0.1700
Data Index: 7986668 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7768. Min Act: -0.1700
Data Index: 3114692 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7455. Min Act: -0.1700
Data Index: 5444140 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 5317136 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7143. Min Act: -0.1700
Data Index: 6872788 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7143. Min Act: -0.1700
Data Index: 4927007 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7143. Min Act: -0.1700
Data Index: 7085081 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7143. Min Act: -0.1700
Data Index: 6519454 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.7143. Min Act: -0.1700
Data Index: 8806349 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 4904038 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2137204 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 7190948 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 879124 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9018. Min Range: -4.9018
Max Act: 4.6830. Min Act: -0.1700
Data Index: 1630038 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19