Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.2373. Min Act: -0.1700
Data Index: 4306798 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.0799. Min Act: -0.1700
Data Index: 4045972 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.0483. Min Act: -0.1700
Data Index: 6415180 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2373. Min Range: -3.2373
Max Act: 3.0168. Min Act: -0.1700
Data Index: 5163276 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9377. Min Act: -0.1700
Data Index: 5801731 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9219. Min Act: -0.1700
Data Index: 1565017 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8901. Min Act: -0.1700
Data Index: 3667733 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.9060. Min Act: -0.1700
Data Index: 1301879 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8266. Min Act: -0.1700
Data Index: 5210890 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 8334512 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.8107. Min Act: -0.1700
Data Index: 972984 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7788. Min Act: -0.1700
Data Index: 6707835 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7788. Min Act: -0.1700
Data Index: 7998153 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7948. Min Act: -0.1700
Data Index: 7811366 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7948. Min Act: -0.1700
Data Index: 1039850 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 2482420 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7788. Min Act: -0.1700
Data Index: 626516 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 8146339 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 3195615 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2373. Min Range: -3.2373
Max Act: 2.7629. Min Act: -0.1700
Data Index: 5457861 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19