Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.2917. Min Act: -0.1700
Data Index: 8531261 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.2292. Min Act: -0.1700
Data Index: 4279086 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.1980. Min Act: -0.1700
Data Index: 7644009 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.1980. Min Act: -0.1700
Data Index: 875436 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.0417. Min Act: -0.1700
Data Index: 6961644 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.0105. Min Act: -0.1700
Data Index: 8057127 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9792. Min Act: -0.1700
Data Index: 1747464 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9792. Min Act: -0.1700
Data Index: 3557668 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2917. Min Range: -7.2917
Max Act: 7.0105. Min Act: -0.1700
Data Index: 6666255 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9480. Min Act: -0.1700
Data Index: 2257432 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9480. Min Act: -0.1700
Data Index: 349088 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9792. Min Act: -0.1700
Data Index: 1971762 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.9167. Min Act: -0.1700
Data Index: 5888380 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8855. Min Act: -0.1700
Data Index: 200882 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8855. Min Act: -0.1700
Data Index: 7085689 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8855. Min Act: -0.1700
Data Index: 3682158 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8230. Min Act: -0.1700
Data Index: 2614264 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8542. Min Act: -0.1700
Data Index: 4738162 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8230. Min Act: -0.1700
Data Index: 3682921 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2917. Min Range: -7.2917
Max Act: 6.8230. Min Act: -0.1700
Data Index: 5263084 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19