Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.4746. Min Act: -0.1700
Data Index: 977854 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.3808. Min Act: -0.1700
Data Index: 642394 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.3183. Min Act: -0.1700
Data Index: 7197700 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.3183. Min Act: -0.1700
Data Index: 7622289 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.3183. Min Act: -0.1700
Data Index: 7781548 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.2871. Min Act: -0.1700
Data Index: 2947440 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.2871. Min Act: -0.1700
Data Index: 2672971 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.2246. Min Act: -0.1700
Data Index: 315863 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.1621. Min Act: -0.1700
Data Index: 4484335 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.1621. Min Act: -0.1700
Data Index: 8021321 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.1308. Min Act: -0.1700
Data Index: 4132012 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0683. Min Act: -0.1700
Data Index: 3789095 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0683. Min Act: -0.1700
Data Index: 8634882 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5018091 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0683. Min Act: -0.1700
Data Index: 5475889 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0371. Min Act: -0.1700
Data Index: 404873 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0058. Min Act: -0.1700
Data Index: 8682735 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4746. Min Range: -5.4746
Max Act: 5.0058. Min Act: -0.1700
Data Index: 6814814 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4746. Min Range: -5.4746
Max Act: 4.9746. Min Act: -0.1700
Data Index: 3755795 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4746. Min Range: -5.4746
Max Act: 4.9433. Min Act: -0.1700
Data Index: 1573768 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19