Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5639 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.5988. Min Act: -0.1700
Data Index: 8358706 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.4738. Min Act: -0.1700
Data Index: 3497722 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.4426. Min Act: -0.1700
Data Index: 5787481 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2863. Min Act: -0.1700
Data Index: 6798674 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.3176. Min Act: -0.1700
Data Index: 36047 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2863. Min Act: -0.1700
Data Index: 3976738 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2551. Min Act: -0.1700
Data Index: 4655655 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2551. Min Act: -0.1700
Data Index: 4946924 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2238. Min Act: -0.1700
Data Index: 832584 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1926. Min Act: -0.1700
Data Index: 3719054 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.2238. Min Act: -0.1700
Data Index: 3907394 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1613. Min Act: -0.1700
Data Index: 7597405 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1613. Min Act: -0.1700
Data Index: 4861631 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1613. Min Act: -0.1700
Data Index: 711747 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4064077 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1301. Min Act: -0.1700
Data Index: 225160 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.1301. Min Act: -0.1700
Data Index: 1718001 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.0988. Min Act: -0.1700
Data Index: 7802832 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.0988. Min Act: -0.1700
Data Index: 438798 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5988. Min Range: -6.5988
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1985358 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19