Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.2988. Min Act: -0.1700
Data Index: 4408639 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.2988. Min Act: -0.1700
Data Index: 2726074 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.2675. Min Act: -0.1700
Data Index: 5106537 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.2675. Min Act: -0.1700
Data Index: 4453060 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.2050. Min Act: -0.1700
Data Index: 570559 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1738. Min Act: -0.1700
Data Index: 4783402 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1738. Min Act: -0.1700
Data Index: 4783400 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1738. Min Act: -0.1700
Data Index: 6939830 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1113. Min Act: -0.1700
Data Index: 4349951 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1425. Min Act: -0.1700
Data Index: 6058262 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1425. Min Act: -0.1700
Data Index: 2628673 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1113. Min Act: -0.1700
Data Index: 8070687 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1425. Min Act: -0.1700
Data Index: 2295916 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.0800. Min Act: -0.1700
Data Index: 6616557 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1113. Min Act: -0.1700
Data Index: 7384377 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.0800. Min Act: -0.1700
Data Index: 3134867 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.1113. Min Act: -0.1700
Data Index: 1506188 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.0800. Min Act: -0.1700
Data Index: 2571901 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.0800. Min Act: -0.1700
Data Index: 8771390 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2988. Min Range: -5.2988
Max Act: 5.0800. Min Act: -0.1700
Data Index: 3537311 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19