Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.3036. Min Act: -0.1700
Data Index: 3158263 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.2565. Min Act: -0.1700
Data Index: 106012 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.1779. Min Act: -0.1700
Data Index: 2857331 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.1464. Min Act: -0.1700
Data Index: 2129312 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.1464. Min Act: -0.1700
Data Index: 4255077 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.1149. Min Act: -0.1700
Data Index: 2693326 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0834. Min Act: -0.1700
Data Index: 5225414 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0518. Min Act: -0.1700
Data Index: 8449075 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0518. Min Act: -0.1700
Data Index: 7265386 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0518. Min Act: -0.1700
Data Index: 538527 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0361. Min Act: -0.1700
Data Index: 7429303 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0361. Min Act: -0.1700
Data Index: 6262730 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0203. Min Act: -0.1700
Data Index: 4301060 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0203. Min Act: -0.1700
Data Index: 8193581 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0361. Min Act: -0.1700
Data Index: 5532019 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3036. Min Range: -3.3036
Max Act: 2.9887. Min Act: -0.1700
Data Index: 6287009 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0045. Min Act: -0.1700
Data Index: 1239274 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0045. Min Act: -0.1700
Data Index: 3581550 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0045. Min Act: -0.1700
Data Index: 2857322 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3036. Min Range: -3.3036
Max Act: 3.0045. Min Act: -0.1700
Data Index: 5408651 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19