Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.7285. Min Act: -0.1700
Data Index: 7884413 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.5098. Min Act: -0.1700
Data Index: 1072567 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4785. Min Act: -0.1700
Data Index: 7195512 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4160. Min Act: -0.1700
Data Index: 167572 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4160. Min Act: -0.1700
Data Index: 6691568 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.4160. Min Act: -0.1700
Data Index: 427483 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3848. Min Act: -0.1700
Data Index: 1834231 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3535. Min Act: -0.1700
Data Index: 5428282 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3535. Min Act: -0.1700
Data Index: 3215871 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3535. Min Act: -0.1700
Data Index: 6842322 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3223. Min Act: -0.1700
Data Index: 397058 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3223. Min Act: -0.1700
Data Index: 6095574 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.3223. Min Act: -0.1700
Data Index: 5516776 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.2598. Min Act: -0.1700
Data Index: 7673216 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.2285. Min Act: -0.1700
Data Index: 6328272 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.1973. Min Act: -0.1700
Data Index: 5743186 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.1660. Min Act: -0.1700
Data Index: 5060498 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.1660. Min Act: -0.1700
Data Index: 3022382 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.1660. Min Act: -0.1700
Data Index: 1245601 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7285. Min Range: -6.7285
Max Act: 6.1348. Min Act: -0.1700
Data Index: 2577416 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19