Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4321 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.3129. Min Act: -0.1700
Data Index: 6304673 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.2816. Min Act: -0.1700
Data Index: 4183878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.2191. Min Act: -0.1700
Data Index: 8677981 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.1254. Min Act: -0.1700
Data Index: 7006620 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.1254. Min Act: -0.1700
Data Index: 3418001 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.1254. Min Act: -0.1700
Data Index: 1268797 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.1254. Min Act: -0.1700
Data Index: 3037874 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2097956 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 6002892 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2953550 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2448997 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 7539597 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2441745 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0941. Min Act: -0.1700
Data Index: 7137912 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 888902 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0316. Min Act: -0.1700
Data Index: 3241278 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 3517495 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 2096293 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 3554451 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3129. Min Range: -4.3129
Max Act: 4.0629. Min Act: -0.1700
Data Index: 2182894 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19