Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.8077. Min Act: -0.1700
Data Index: 984101 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.7452. Min Act: -0.1700
Data Index: 6622640 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.7452. Min Act: -0.1700
Data Index: 8074550 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.6515. Min Act: -0.1700
Data Index: 5978788 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5890. Min Act: -0.1700
Data Index: 2826391 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5890. Min Act: -0.1700
Data Index: 8643607 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.6202. Min Act: -0.1700
Data Index: 2831460 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.6202. Min Act: -0.1700
Data Index: 984099 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5577. Min Act: -0.1700
Data Index: 5101168 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5577. Min Act: -0.1700
Data Index: 4223190 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5265. Min Act: -0.1700
Data Index: 1284375 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5265. Min Act: -0.1700
Data Index: 7883005 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 5533112 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.5265. Min Act: -0.1700
Data Index: 8262026 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 7520251 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 1880801 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 787306 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 96768 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4952. Min Act: -0.1700
Data Index: 8739337 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8077. Min Range: -4.8077
Max Act: 4.4640. Min Act: -0.1700
Data Index: 8008362 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19