Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1650. Min Range: -9.1650
Max Act: 9.1650. Min Act: -0.1700
Data Index: 7915102 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1650. Min Range: -9.1650
Max Act: 9.1650. Min Act: -0.1700
Data Index: 6283548 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1650. Min Range: -9.1650
Max Act: 9.1650. Min Act: -0.1700
Data Index: 2230345 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.8525. Min Act: -0.1700
Data Index: 2440602 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.7900. Min Act: -0.1700
Data Index: 7344078 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.6650. Min Act: -0.1700
Data Index: 1524150 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.6650. Min Act: -0.1700
Data Index: 4685555 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.6650. Min Act: -0.1700
Data Index: 1723690 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.5400. Min Act: -0.1700
Data Index: 519924 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.6025. Min Act: -0.1700
Data Index: 3038920 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.6025. Min Act: -0.1700
Data Index: 5993789 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.5400. Min Act: -0.1700
Data Index: 4410159 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.5400. Min Act: -0.1700
Data Index: 6349084 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.5400. Min Act: -0.1700
Data Index: 5832831 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 2906133 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 1145060 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 3376155 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 7247407 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 604407 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1650. Min Range: -9.1650
Max Act: 8.4775. Min Act: -0.1700
Data Index: 3206494 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19