Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 200 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.8345. Min Act: -0.1700
Data Index: 173051 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.6782. Min Act: -0.1700
Data Index: 4994127 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5845. Min Act: -0.1700
Data Index: 6011043 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5532. Min Act: -0.1700
Data Index: 89212 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5532. Min Act: -0.1700
Data Index: 1272158 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 4169663 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4595. Min Act: -0.1700
Data Index: 2146100 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4282. Min Act: -0.1700
Data Index: 6638722 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3945473 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.3345. Min Act: -0.1700
Data Index: 4732511 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.3345. Min Act: -0.1700
Data Index: 1662217 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.3032. Min Act: -0.1700
Data Index: 2072297 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2720. Min Act: -0.1700
Data Index: 1372510 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2720. Min Act: -0.1700
Data Index: 3672291 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2407. Min Act: -0.1700
Data Index: 6414599 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2095. Min Act: -0.1700
Data Index: 1372506 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2407. Min Act: -0.1700
Data Index: 4345997 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2407. Min Act: -0.1700
Data Index: 4868260 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2095. Min Act: -0.1700
Data Index: 4923187 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.2095. Min Act: -0.1700
Data Index: 4507701 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19