Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 5538747 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.5883. Min Act: -0.1700
Data Index: 8784420 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.5570. Min Act: -0.1700
Data Index: 768618 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.5258. Min Act: -0.1700
Data Index: 7031680 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.3383. Min Act: -0.1700
Data Index: 2119491 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.3383. Min Act: -0.1700
Data Index: 3196951 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.3070. Min Act: -0.1700
Data Index: 5328589 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.2133. Min Act: -0.1700
Data Index: 5991581 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.2133. Min Act: -0.1700
Data Index: 4062458 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.1820. Min Act: -0.1700
Data Index: 8109520 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.1820. Min Act: -0.1700
Data Index: 2106555 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.1820. Min Act: -0.1700
Data Index: 3436551 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.1508. Min Act: -0.1700
Data Index: 3970241 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.1508. Min Act: -0.1700
Data Index: 1840 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.0883. Min Act: -0.1700
Data Index: 3104967 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.0883. Min Act: -0.1700
Data Index: 3698901 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.0570. Min Act: -0.1700
Data Index: 4643684 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5883. Min Range: -7.5883
Max Act: 7.0258. Min Act: -0.1700
Data Index: 6598317 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5883. Min Range: -7.5883
Max Act: 6.9945. Min Act: -0.1700
Data Index: 3628766 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5883. Min Range: -7.5883
Max Act: 6.9633. Min Act: -0.1700
Data Index: 4373817 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19