Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6258 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2770. Min Act: -0.1619
Data Index: 3345250 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2770. Min Act: -0.1540
Data Index: 220727 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2417. Min Act: -0.1660
Data Index: 4355682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2241. Min Act: -0.1690
Data Index: 8068600 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1713. Min Act: -0.1699
Data Index: 2729839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1889. Min Act: -0.1696
Data Index: 8469555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2065. Min Act: -0.1682
Data Index: 8764269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1186. Min Act: -0.1401
Data Index: 6569456 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1186. Min Act: -0.1700
Data Index: 7208775 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1186. Min Act: -0.1687
Data Index: 8165333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0835. Min Act: -0.1661
Data Index: 8804051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1010. Min Act: -0.1699
Data Index: 6546609 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0835. Min Act: -0.1616
Data Index: 4136055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0835. Min Act: -0.1505
Data Index: 7997677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0835. Min Act: -0.1589
Data Index: 387047 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0835. Min Act: -0.1685
Data Index: 2594157 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0661. Min Act: -0.1485
Data Index: 5361199 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0661. Min Act: -0.1529
Data Index: 698881 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0661. Min Act: -0.1698
Data Index: 8015527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0661. Min Act: -0.1308
Data Index: 93795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19