Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4311 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.3972. Min Act: -0.1700
Data Index: 7237303 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.3972. Min Act: -0.1700
Data Index: 4936603 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.3972. Min Act: -0.1700
Data Index: 3874169 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.2717. Min Act: -0.1700
Data Index: 2970492 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.2559. Min Act: -0.1700
Data Index: 2531889 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.2402. Min Act: -0.1700
Data Index: 3445219 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.2402. Min Act: -0.1700
Data Index: 2531899 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.2245. Min Act: -0.1700
Data Index: 3022289 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1773. Min Act: -0.1700
Data Index: 1836745 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1931. Min Act: -0.1700
Data Index: 337193 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1773. Min Act: -0.1700
Data Index: 8228528 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1773. Min Act: -0.1700
Data Index: 4101711 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1459. Min Act: -0.1700
Data Index: 1312520 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1459. Min Act: -0.1700
Data Index: 2566155 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1301. Min Act: -0.1700
Data Index: 2021563 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1301. Min Act: -0.1700
Data Index: 8192848 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.1144. Min Act: -0.1700
Data Index: 8367508 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.0986. Min Act: -0.1700
Data Index: 6614639 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.0986. Min Act: -0.1700
Data Index: 6846406 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3972. Min Range: -3.3972
Max Act: 3.0828. Min Act: -0.1700
Data Index: 5740288 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19