Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.3757. Min Act: -0.1700
Data Index: 5970201 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.1569. Min Act: -0.1700
Data Index: 142695 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0632. Min Act: -0.1700
Data Index: 1905524 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0944. Min Act: -0.1700
Data Index: 8072177 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0319. Min Act: -0.1700
Data Index: 783807 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4419590 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0632. Min Act: -0.1700
Data Index: 8201177 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0319. Min Act: -0.1700
Data Index: 3463208 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0007. Min Act: -0.1700
Data Index: 166964 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3757. Min Range: -5.3757
Max Act: 5.0319. Min Act: -0.1700
Data Index: 4252511 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 968064 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4877953 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 5414071 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1020869 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1698
Data Index: 3273231 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 7470060 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 4377289 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 977534 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 2215403 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3757. Min Range: -5.3757
Max Act: 4.9694. Min Act: -0.1700
Data Index: 6957118 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19