Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6138 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.6286. Min Act: -0.1700
Data Index: 7199808 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.5348. Min Act: -0.1700
Data Index: 3519296 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2848. Min Act: -0.1700
Data Index: 8194116 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2848. Min Act: -0.1700
Data Index: 6085290 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2536. Min Act: -0.1700
Data Index: 8368800 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2536. Min Act: -0.1700
Data Index: 6585512 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2223. Min Act: -0.1700
Data Index: 4033023 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.2223. Min Act: -0.1700
Data Index: 1145339 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 7425573 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 7393691 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 4865128 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 8067659 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 5684690 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 7298973 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 7948486 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1911. Min Act: -0.1700
Data Index: 179185 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 857258 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 2807924 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 2615569 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6286. Min Range: -6.6286
Max Act: 6.1598. Min Act: -0.1700
Data Index: 4912210 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19