Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.4147. Min Act: -0.1700
Data Index: 974034 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.4147. Min Act: -0.1700
Data Index: 681175 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.2272. Min Act: -0.1700
Data Index: 3829364 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1960. Min Act: -0.1700
Data Index: 2768814 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1960. Min Act: -0.1700
Data Index: 6784567 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1647. Min Act: -0.1700
Data Index: 1934555 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1647. Min Act: -0.1700
Data Index: 534496 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1335. Min Act: -0.1700
Data Index: 6189871 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1335. Min Act: -0.1700
Data Index: 6165331 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.1022. Min Act: -0.1700
Data Index: 4746387 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0710. Min Act: -0.1700
Data Index: 1102098 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0710. Min Act: -0.1700
Data Index: 3968138 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0710. Min Act: -0.1700
Data Index: 4257521 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 6591406 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 4779701 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 7455878 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 497165 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 3956742 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 1450574 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4147. Min Range: -4.4147
Max Act: 4.0397. Min Act: -0.1700
Data Index: 7481351 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19