Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 917 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4631. Min Act: -0.1700
Data Index: 7414752 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4006. Min Act: -0.1700
Data Index: 5635259 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.4319. Min Act: -0.1700
Data Index: 1204383 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3694. Min Act: -0.1700
Data Index: 1609499 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3381. Min Act: -0.1700
Data Index: 4188269 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2756. Min Act: -0.1700
Data Index: 6742045 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2756. Min Act: -0.1700
Data Index: 3542626 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2756. Min Act: -0.1700
Data Index: 4620938 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.3069. Min Act: -0.1700
Data Index: 5768245 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2131. Min Act: -0.1700
Data Index: 5454430 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1819. Min Act: -0.1700
Data Index: 5037957 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2131. Min Act: -0.1700
Data Index: 3466489 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1819. Min Act: -0.1700
Data Index: 5214774 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2131. Min Act: -0.1700
Data Index: 1359841 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1506. Min Act: -0.1700
Data Index: 2761426 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.2444. Min Act: -0.1700
Data Index: 4052485 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1819. Min Act: -0.1700
Data Index: 4367458 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1506. Min Act: -0.1700
Data Index: 950628 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1194. Min Act: -0.1700
Data Index: 755330 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4631. Min Range: -6.4631
Max Act: 6.1194. Min Act: -0.1700
Data Index: 2882462 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19