Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4113. Min Range: -6.4113
Max Act: 6.4113. Min Act: -0.1700
Data Index: 7841172 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4113. Min Range: -6.4113
Max Act: 6.0050. Min Act: -0.1700
Data Index: 8235863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.8488. Min Act: -0.1700
Data Index: 7841171 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.7550. Min Act: -0.1700
Data Index: 3087682 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5988. Min Act: -0.1700
Data Index: 1537405 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5675. Min Act: -0.1700
Data Index: 8469030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5675. Min Act: -0.1700
Data Index: 2968003 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5675. Min Act: -0.1700
Data Index: 3617661 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5675. Min Act: -0.1700
Data Index: 6456268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5363. Min Act: -0.1700
Data Index: 4880534 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5363. Min Act: -0.1700
Data Index: 8758079 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5050. Min Act: -0.1700
Data Index: 200104 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.5050. Min Act: -0.1700
Data Index: 6628777 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4425. Min Act: -0.1700
Data Index: 4687506 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4425. Min Act: -0.1700
Data Index: 1155293 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4425. Min Act: -0.1700
Data Index: 7811768 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4425. Min Act: -0.1700
Data Index: 4202474 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 1129609 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4113. Min Act: -0.1699
Data Index: 4455225 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4113. Min Range: -6.4113
Max Act: 5.4113. Min Act: -0.1700
Data Index: 1270756 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19