Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1734 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.8643. Min Act: -0.1700
Data Index: 2382125 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.7706. Min Act: -0.1700
Data Index: 8421081 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.6456. Min Act: -0.1700
Data Index: 1863113 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.6143. Min Act: -0.1700
Data Index: 2615820 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.6143. Min Act: -0.1700
Data Index: 8368320 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.5518. Min Act: -0.1700
Data Index: 5580028 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4893. Min Act: -0.1700
Data Index: 699060 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4581. Min Act: -0.1700
Data Index: 8108642 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4581. Min Act: -0.1700
Data Index: 763148 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4581. Min Act: -0.1700
Data Index: 8635935 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4581. Min Act: -0.1700
Data Index: 7733463 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3956. Min Act: -0.1700
Data Index: 3268944 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.4268. Min Act: -0.1700
Data Index: 4357401 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3956. Min Act: -0.1700
Data Index: 5712926 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 1627 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3144993 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 5466112 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6413398 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 5567591 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8643. Min Range: -5.8643
Max Act: 5.3643. Min Act: -0.1700
Data Index: 2868026 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19