Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.9807. Min Act: -0.1700
Data Index: 7477590 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.2932. Min Act: -0.1700
Data Index: 4879839 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.1682. Min Act: -0.1700
Data Index: 7960594 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.1682. Min Act: -0.1700
Data Index: 2225363 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.1682. Min Act: -0.1700
Data Index: 4836735 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.1057. Min Act: -0.1700
Data Index: 4216956 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0745. Min Act: -0.1700
Data Index: 7641172 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0120. Min Act: -0.1700
Data Index: 7686670 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0120. Min Act: -0.1700
Data Index: 1195092 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0432. Min Act: -0.1700
Data Index: 2902199 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0120. Min Act: -0.1700
Data Index: 6188597 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.9807. Min Act: -0.1700
Data Index: 8483739 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9807. Min Range: -8.9807
Max Act: 8.0120. Min Act: -0.1700
Data Index: 5945287 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.9495. Min Act: -0.1700
Data Index: 1847065 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.8870. Min Act: -0.1700
Data Index: 2541336 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.9495. Min Act: -0.1700
Data Index: 4881201 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.8870. Min Act: -0.1700
Data Index: 6976850 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.8557. Min Act: -0.1700
Data Index: 3216977 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.8870. Min Act: -0.1700
Data Index: 2387960 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9807. Min Range: -8.9807
Max Act: 7.8870. Min Act: -0.1700
Data Index: 5041011 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19