Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6243. Min Range: -6.6243
Max Act: 6.6243. Min Act: -0.1700
Data Index: 7529617 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6243. Min Range: -6.6243
Max Act: 6.2180. Min Act: -0.1700
Data Index: 1207639 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5030056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1923850 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4069145 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.7180. Min Act: -0.1700
Data Index: 8269879 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6868. Min Act: -0.1700
Data Index: 7174494 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6555. Min Act: -0.1700
Data Index: 3433446 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6555. Min Act: -0.1700
Data Index: 2698518 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6868. Min Act: -0.1700
Data Index: 5879710 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6555. Min Act: -0.1700
Data Index: 209057 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.6243. Min Act: -0.1700
Data Index: 547701 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5305. Min Act: -0.1700
Data Index: 406914 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5305. Min Act: -0.1700
Data Index: 1051736 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5305. Min Act: -0.1700
Data Index: 2330812 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5618. Min Act: -0.1687
Data Index: 2002748 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5618. Min Act: -0.1700
Data Index: 7285184 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.4993. Min Act: -0.1700
Data Index: 8452518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.5305. Min Act: -0.1700
Data Index: 5988810 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6243. Min Range: -6.6243
Max Act: 5.4680. Min Act: -0.1699
Data Index: 5776403 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19