Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.7814. Min Act: -0.1700
Data Index: 7144244 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.7189. Min Act: -0.1700
Data Index: 5603981 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.6876. Min Act: -0.1700
Data Index: 2469739 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.6876. Min Act: -0.1700
Data Index: 2721544 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.6563. Min Act: -0.1700
Data Index: 5455268 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.6250. Min Act: -0.1700
Data Index: 6501806 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.5937. Min Act: -0.1700
Data Index: 5561934 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.5937. Min Act: -0.1700
Data Index: 4572102 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.5311. Min Act: -0.1700
Data Index: 3046438 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.5311. Min Act: -0.1700
Data Index: 68616 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4998. Min Act: -0.1700
Data Index: 7296277 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4684. Min Act: -0.1700
Data Index: 4610519 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4684. Min Act: -0.1700
Data Index: 2745777 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4684. Min Act: -0.1700
Data Index: 7920523 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4684. Min Act: -0.1700
Data Index: 4559961 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4371. Min Act: -0.1700
Data Index: 27700 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4371. Min Act: -0.1700
Data Index: 1667272 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4371. Min Act: -0.1700
Data Index: 4722970 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4371. Min Act: -0.1700
Data Index: 5524276 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7814. Min Range: -3.7814
Max Act: 3.4057. Min Act: -0.1700
Data Index: 2503075 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19