Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.5240. Min Act: -0.1700
Data Index: 3414683 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.4615. Min Act: -0.1443
Data Index: 7090944 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.4615. Min Act: -0.1659
Data Index: 3863069 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3990. Min Act: -0.1699
Data Index: 5679957 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3365. Min Act: -0.1700
Data Index: 3226771 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3365. Min Act: -0.0180
Data Index: 3226770 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3365. Min Act: -0.1649
Data Index: 2776927 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3365. Min Act: -0.1677
Data Index: 5271017 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2740. Min Act: -0.1690
Data Index: 8572294 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2740. Min Act: -0.0977
Data Index: 1353539 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2740. Min Act: -0.1656
Data Index: 3992778 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.3365. Min Act: -0.1604
Data Index: 7090943 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2740. Min Act: -0.1700
Data Index: 5679952 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2115. Min Act: -0.0726
Data Index: 3992779 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2115. Min Act: -0.1690
Data Index: 2776926 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2115. Min Act: -0.0677
Data Index: 7578867 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2115. Min Act: -0.1622
Data Index: 410815 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.2115. Min Act: -0.1700
Data Index: 613362 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.1490. Min Act: -0.1699
Data Index: 3074751 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5240. Min Range: -7.5240
Max Act: 7.1490. Min Act: -0.1700
Data Index: 544046 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19