Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1744 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4929. Min Act: -0.1699
Data Index: 5140713 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4754. Min Act: -0.1699
Data Index: 766662 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4666. Min Act: -0.1700
Data Index: 6163644 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4578. Min Act: -0.1700
Data Index: 6299696 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4754. Min Act: -0.1700
Data Index: 5490331 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4666. Min Act: -0.1698
Data Index: 1089857 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 5115949 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 5741594 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 7446871 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4402. Min Act: -0.1700
Data Index: 7205964 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4314. Min Act: -0.1700
Data Index: 1419516 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 4960650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1627
Data Index: 6814818 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 378311 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.4226. Min Act: -0.1700
Data Index: 1423535 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.3962. Min Act: -0.1693
Data Index: 4456938 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.3873. Min Act: -0.1699
Data Index: 5481932 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.3962. Min Act: -0.1700
Data Index: 4322167 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.3873. Min Act: -0.1700
Data Index: 993770 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4929. Min Range: -1.4929
Max Act: 1.3962. Min Act: -0.1695
Data Index: 5910326 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19