Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.1783. Min Act: -0.1700
Data Index: 171095 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.2096. Min Act: -0.1700
Data Index: 5724073 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.2096. Min Act: -0.1700
Data Index: 8600564 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.1471. Min Act: -0.1700
Data Index: 2750960 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.1158. Min Act: -0.1700
Data Index: 2336388 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.0533. Min Act: -0.1700
Data Index: 5366964 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2096. Min Range: -5.2096
Max Act: 5.0533. Min Act: -0.1700
Data Index: 7336445 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9908. Min Act: -0.1700
Data Index: 1927821 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9596. Min Act: -0.1700
Data Index: 1356031 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9596. Min Act: -0.1700
Data Index: 1913294 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9596. Min Act: -0.1700
Data Index: 2347803 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9596. Min Act: -0.1700
Data Index: 4458090 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9596. Min Act: -0.1700
Data Index: 4158732 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.8971. Min Act: -0.1700
Data Index: 7454192 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 6883736 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 7572101 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 5962058 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 8309849 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 5348617 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2096. Min Range: -5.2096
Max Act: 4.9283. Min Act: -0.1700
Data Index: 7983979 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19