Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6329 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.8197. Min Act: -0.1700
Data Index: 2694244 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.8197. Min Act: -0.1700
Data Index: 955427 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.7884. Min Act: -0.1700
Data Index: 3594175 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.7572. Min Act: -0.1700
Data Index: 4215938 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.7884. Min Act: -0.1700
Data Index: 2512813 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.5697. Min Act: -0.1700
Data Index: 850085 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.5384. Min Act: -0.1700
Data Index: 1313394 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.5072. Min Act: -0.1700
Data Index: 7466086 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4759. Min Act: -0.1700
Data Index: 932586 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4447. Min Act: -0.1700
Data Index: 1136617 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4134. Min Act: -0.1700
Data Index: 4256667 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3197. Min Act: -0.1700
Data Index: 4739570 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3822. Min Act: -0.1700
Data Index: 2871164 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3509. Min Act: -0.1700
Data Index: 390293 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2884. Min Act: -0.1700
Data Index: 3146865 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2259. Min Act: -0.1700
Data Index: 8396474 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2259. Min Act: -0.1700
Data Index: 4074233 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2259. Min Act: -0.1700
Data Index: 6359280 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.1947. Min Act: -0.1700
Data Index: 3050331 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.1634. Min Act: -0.1700
Data Index: 633473 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19