Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1214 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1003. Min Range: -9.1003
Max Act: 9.1003. Min Act: -0.1700
Data Index: 4664656 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.8503. Min Act: -0.1700
Data Index: 5559097 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.8503. Min Act: -0.1700
Data Index: 8601803 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.7253. Min Act: -0.1700
Data Index: 2677508 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.7253. Min Act: -0.1700
Data Index: 1375325 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.7253. Min Act: -0.1700
Data Index: 5581265 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.3503. Min Act: -0.1700
Data Index: 965492 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.3503. Min Act: -0.1700
Data Index: 6228067 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.2253. Min Act: -0.1700
Data Index: 7368433 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.2253. Min Act: -0.1700
Data Index: 8172266 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.2253. Min Act: -0.1700
Data Index: 2315038 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.2253. Min Act: -0.1700
Data Index: 6845628 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 7257665 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 3769966 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 6014824 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 33745 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 2961528 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 5324582 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 1086861 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1003. Min Range: -9.1003
Max Act: 8.1628. Min Act: -0.1700
Data Index: 683436 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19