Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5579 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.7434. Min Act: -0.1700
Data Index: 1684608 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.3684. Min Act: -0.1700
Data Index: 1594595 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.2434. Min Act: -0.1700
Data Index: 4853678 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.2434. Min Act: -0.1700
Data Index: 4843565 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.2434. Min Act: -0.1700
Data Index: 5983626 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.1809. Min Act: -0.1700
Data Index: 1225497 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.1184. Min Act: -0.1700
Data Index: 7130050 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.0559. Min Act: -0.1700
Data Index: 4854839 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.0559. Min Act: -0.1700
Data Index: 4247276 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.0559. Min Act: -0.1700
Data Index: 6071482 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.0559. Min Act: -0.1700
Data Index: 7126703 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7434. Min Range: -8.7434
Max Act: 8.0559. Min Act: -0.1700
Data Index: 208706 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.9309. Min Act: -0.1700
Data Index: 5834245 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8684. Min Act: -0.1700
Data Index: 7082248 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8684. Min Act: -0.1700
Data Index: 7981798 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8059. Min Act: -0.1700
Data Index: 2274885 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8059. Min Act: -0.1700
Data Index: 1528475 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8059. Min Act: -0.1700
Data Index: 353883 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8059. Min Act: -0.1700
Data Index: 7126324 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7434. Min Range: -8.7434
Max Act: 7.8059. Min Act: -0.1700
Data Index: 2558440 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19