Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3967 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2803. Min Range: -8.2803
Max Act: 8.2803. Min Act: -0.1700
Data Index: 8178075 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.8428. Min Act: -0.1700
Data Index: 7993445 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.7178. Min Act: -0.1700
Data Index: 4483800 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.6553. Min Act: -0.1700
Data Index: 5065067 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.5303. Min Act: -0.1700
Data Index: 7105198 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.5303. Min Act: -0.1700
Data Index: 7324785 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.4990. Min Act: -0.1700
Data Index: 5331889 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.4678. Min Act: -0.1700
Data Index: 7702199 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.4365. Min Act: -0.1700
Data Index: 1944861 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.3428. Min Act: -0.1700
Data Index: 4062904 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.3428. Min Act: -0.1700
Data Index: 7130123 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.3428. Min Act: -0.1700
Data Index: 8182902 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.3115. Min Act: -0.1700
Data Index: 3297537 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.3115. Min Act: -0.1700
Data Index: 4734236 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.2490. Min Act: -0.1700
Data Index: 6341592 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.1865. Min Act: -0.1700
Data Index: 5741462 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.1865. Min Act: -0.1700
Data Index: 6478756 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.1865. Min Act: -0.1700
Data Index: 4394343 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.2178. Min Act: -0.1700
Data Index: 600964 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2803. Min Range: -8.2803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 303031 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19