Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0184. Min Range: -7.0184
Max Act: 7.0184. Min Act: -0.1700
Data Index: 7080308 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.9872. Min Act: -0.1700
Data Index: 1820535 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.8934. Min Act: -0.1700
Data Index: 649118 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.8622. Min Act: -0.1700
Data Index: 7005992 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.8309. Min Act: -0.1700
Data Index: 2403104 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.8622. Min Act: -0.1700
Data Index: 5422028 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.7684. Min Act: -0.1700
Data Index: 2687865 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.7372. Min Act: -0.1700
Data Index: 7579235 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.7684. Min Act: -0.1700
Data Index: 6938634 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.7684. Min Act: -0.1700
Data Index: 4751753 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.7372. Min Act: -0.1700
Data Index: 4713709 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6434. Min Act: -0.1700
Data Index: 4083244 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6747. Min Act: -0.1700
Data Index: 5009756 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6747. Min Act: -0.1700
Data Index: 5928510 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6434. Min Act: -0.1700
Data Index: 1329666 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6434. Min Act: -0.1700
Data Index: 565300 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6434. Min Act: -0.1700
Data Index: 5869150 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6122. Min Act: -0.1700
Data Index: 3596109 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6122. Min Act: -0.1700
Data Index: 4332977 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0184. Min Range: -7.0184
Max Act: 6.6122. Min Act: -0.1700
Data Index: 6222856 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19