Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 696 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.6071. Min Act: -0.1700
Data Index: 69600 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.2321. Min Act: -0.1700
Data Index: 4274798 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.1696. Min Act: -0.1700
Data Index: 8741034 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.1696. Min Act: -0.1700
Data Index: 3519103 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0758. Min Act: -0.1700
Data Index: 7958472 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0758. Min Act: -0.1700
Data Index: 1690967 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0133. Min Act: -0.1700
Data Index: 8688417 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0446. Min Act: -0.1700
Data Index: 6177493 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0133. Min Act: -0.1700
Data Index: 37748 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.9821. Min Act: -0.1700
Data Index: 7274718 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6071. Min Range: -6.6071
Max Act: 6.0133. Min Act: -0.1700
Data Index: 5551322 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.9821. Min Act: -0.1700
Data Index: 1797187 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.9508. Min Act: -0.1700
Data Index: 5996600 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8883. Min Act: -0.1700
Data Index: 8765714 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8883. Min Act: -0.1700
Data Index: 2421674 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8571. Min Act: -0.1700
Data Index: 7078380 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8571. Min Act: -0.1700
Data Index: 407526 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8258. Min Act: -0.1700
Data Index: 5543287 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.7946. Min Act: -0.1700
Data Index: 6282348 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6071. Min Range: -6.6071
Max Act: 5.8258. Min Act: -0.1700
Data Index: 5315004 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19