Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.7485. Min Act: -0.1700
Data Index: 3393254 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.7172. Min Act: -0.1700
Data Index: 7523750 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.6860. Min Act: -0.1700
Data Index: 5735667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.6547. Min Act: -0.1700
Data Index: 5611798 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.6235. Min Act: -0.1700
Data Index: 4654148 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.5610. Min Act: -0.1700
Data Index: 2603981 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.4985. Min Act: -0.1700
Data Index: 2740380 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.4672. Min Act: -0.1700
Data Index: 769144 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.4360. Min Act: -0.1700
Data Index: 8614966 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.4360. Min Act: -0.1700
Data Index: 109018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.4360. Min Act: -0.1700
Data Index: 5914718 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3735. Min Act: -0.1700
Data Index: 5300919 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3422. Min Act: -0.1700
Data Index: 8301334 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3735. Min Act: -0.1700
Data Index: 5318493 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3422. Min Act: -0.1700
Data Index: 5509758 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3422. Min Act: -0.1700
Data Index: 5544033 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3735. Min Act: -0.1700
Data Index: 2979118 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3110. Min Act: -0.1700
Data Index: 7194699 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.2797. Min Act: -0.1700
Data Index: 3968697 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7485. Min Range: -6.7485
Max Act: 6.3110. Min Act: -0.1700
Data Index: 2724657 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19