Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.4617. Min Act: -0.1700
Data Index: 12732 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.4305. Min Act: -0.1700
Data Index: 7034837 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.3367. Min Act: -0.1700
Data Index: 873114 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.2117. Min Act: -0.1700
Data Index: 2649523 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.1492. Min Act: -0.1700
Data Index: 5026135 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.1180. Min Act: -0.1700
Data Index: 831374 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0867. Min Act: -0.1700
Data Index: 997880 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0867. Min Act: -0.1700
Data Index: 5431829 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0242. Min Act: -0.1700
Data Index: 5180994 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0242. Min Act: -0.1700
Data Index: 8016209 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0242. Min Act: -0.1700
Data Index: 6781894 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9930. Min Act: -0.1700
Data Index: 156770 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4617. Min Range: -5.4617
Max Act: 5.0242. Min Act: -0.1700
Data Index: 3363418 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9930. Min Act: -0.1700
Data Index: 5135598 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9930. Min Act: -0.1700
Data Index: 5990765 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9930. Min Act: -0.1700
Data Index: 2649445 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9930. Min Act: -0.1700
Data Index: 22293 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 5451708 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 904804 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4617. Min Range: -5.4617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 3532556 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19