Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.5778. Min Act: -0.1700
Data Index: 2310860 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.5153. Min Act: -0.1700
Data Index: 1704797 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.3903. Min Act: -0.1700
Data Index: 7623701 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.3278. Min Act: -0.1700
Data Index: 7959417 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.2965. Min Act: -0.1700
Data Index: 8194587 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.2028. Min Act: -0.1700
Data Index: 2310862 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1403. Min Act: -0.1700
Data Index: 2310858 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1715. Min Act: -0.1700
Data Index: 6801649 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.2028. Min Act: -0.1700
Data Index: 38948 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1403. Min Act: -0.1700
Data Index: 8575900 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1090. Min Act: -0.1700
Data Index: 5488353 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1090. Min Act: -0.1700
Data Index: 7970513 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1090. Min Act: -0.1700
Data Index: 4152838 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1090. Min Act: -0.1700
Data Index: 4751829 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.1090. Min Act: -0.1700
Data Index: 1106756 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 2310867 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 8294838 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6415252 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0465. Min Act: -0.1700
Data Index: 3100335 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5778. Min Range: -5.5778
Max Act: 5.0465. Min Act: -0.1700
Data Index: 3147009 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19