Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5600 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0364. Min Range: -5.0364
Max Act: 5.0364. Min Act: -0.1700
Data Index: 3970553 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.9426. Min Act: -0.1700
Data Index: 4153262 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.9114. Min Act: -0.1700
Data Index: 566180 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.9114. Min Act: -0.1700
Data Index: 981745 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.8489. Min Act: -0.1700
Data Index: 7669376 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.8176. Min Act: -0.1700
Data Index: 8445744 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.7551. Min Act: -0.1700
Data Index: 1618819 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.7864. Min Act: -0.1700
Data Index: 6211445 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.7551. Min Act: -0.1700
Data Index: 5135483 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.7239. Min Act: -0.1700
Data Index: 5750891 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.7239. Min Act: -0.1700
Data Index: 7965733 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6926. Min Act: -0.1700
Data Index: 3818244 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6926. Min Act: -0.1700
Data Index: 8762706 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6926. Min Act: -0.1700
Data Index: 5813191 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6614. Min Act: -0.1700
Data Index: 1828249 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6614. Min Act: -0.1700
Data Index: 6042780 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6614. Min Act: -0.1700
Data Index: 4552316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6301. Min Act: -0.1700
Data Index: 4111593 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6301. Min Act: -0.1699
Data Index: 5919844 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0364. Min Range: -5.0364
Max Act: 4.6301. Min Act: -0.1700
Data Index: 7316559 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19