Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7672. Min Act: -0.1700
Data Index: 1206746 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7360. Min Act: -0.1700
Data Index: 6852695 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7360. Min Act: -0.1700
Data Index: 8637416 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7047. Min Act: -0.1700
Data Index: 8637606 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7047. Min Act: -0.1700
Data Index: 8191609 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.7047. Min Act: -0.1700
Data Index: 5429031 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6422. Min Act: -0.1700
Data Index: 1637024 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6110. Min Act: -0.1700
Data Index: 6464823 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6422. Min Act: -0.1700
Data Index: 8822512 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6422. Min Act: -0.1700
Data Index: 6363150 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6422. Min Act: -0.1700
Data Index: 1084273 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 1064927 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6422. Min Act: -0.1700
Data Index: 2810324 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6110. Min Act: -0.1700
Data Index: 4761234 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.6110. Min Act: -0.1700
Data Index: 41982 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 1868420 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 4787183 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 2991298 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5485. Min Act: -0.1700
Data Index: 6323077 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7672. Min Range: -6.7672
Max Act: 6.5797. Min Act: -0.1700
Data Index: 6880855 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19