Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 633 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.4295. Min Act: -0.1700
Data Index: 4483273 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.4295. Min Act: -0.1700
Data Index: 8360617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.3983. Min Act: -0.1700
Data Index: 2332983 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.3358. Min Act: -0.1700
Data Index: 3033061 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2733. Min Act: -0.1700
Data Index: 5575239 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2733. Min Act: -0.1700
Data Index: 2950697 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.2420. Min Act: -0.1700
Data Index: 5245165 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1795. Min Act: -0.1700
Data Index: 5354875 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 2520664 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 4049892 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1483. Min Act: -0.1700
Data Index: 1810775 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.1170. Min Act: -0.1700
Data Index: 5154161 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 7016895 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 8710479 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 6868503 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0233. Min Act: -0.1700
Data Index: 8166543 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0858. Min Act: -0.1700
Data Index: 4902610 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0233. Min Act: -0.1700
Data Index: 4366890 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 8166540 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0545. Min Act: -0.1700
Data Index: 6102008 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19