Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.7993. Min Act: -0.1700
Data Index: 6937360 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.7681. Min Act: -0.1700
Data Index: 5605421 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.7368. Min Act: -0.1700
Data Index: 8565689 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.7056. Min Act: -0.1700
Data Index: 3171048 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6743. Min Act: -0.1700
Data Index: 4849210 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6743. Min Act: -0.1700
Data Index: 775300 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6743. Min Act: -0.1700
Data Index: 6237631 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6743. Min Act: -0.1700
Data Index: 1481672 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 251548 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6431. Min Act: -0.1700
Data Index: 8078598 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6431. Min Act: -0.1700
Data Index: 299076 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 575554 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6431. Min Act: -0.1700
Data Index: 6541970 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 4574826 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 7858238 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 3896213 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.6118. Min Act: -0.1700
Data Index: 1305490 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.5806. Min Act: -0.1700
Data Index: 4701819 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.5493. Min Act: -0.1700
Data Index: 575557 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7993. Min Range: -6.7993
Max Act: 6.5493. Min Act: -0.1700
Data Index: 1656397 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19