Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1889. Min Range: -6.1889
Max Act: 6.1889. Min Act: -0.1700
Data Index: 393070 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.9701. Min Act: -0.1700
Data Index: 1720355 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.9389. Min Act: -0.1700
Data Index: 3845233 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.9076. Min Act: -0.1700
Data Index: 256016 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4541973 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8451. Min Act: -0.1700
Data Index: 3989730 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8451. Min Act: -0.1700
Data Index: 5385996 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8451. Min Act: -0.1700
Data Index: 3810491 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8451. Min Act: -0.1700
Data Index: 3372975 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8451. Min Act: -0.1700
Data Index: 115400 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.8139. Min Act: -0.1700
Data Index: 3447014 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.7201. Min Act: -0.1700
Data Index: 8785639 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.7201. Min Act: -0.1700
Data Index: 2624862 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.7201. Min Act: -0.1700
Data Index: 1975442 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.7201. Min Act: -0.1700
Data Index: 7477122 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.6889. Min Act: -0.1700
Data Index: 2740618 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.6889. Min Act: -0.1700
Data Index: 167476 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.6576. Min Act: -0.1700
Data Index: 5775366 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.6576. Min Act: -0.1700
Data Index: 1498937 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1889. Min Range: -6.1889
Max Act: 5.6576. Min Act: -0.1700
Data Index: 2525696 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19