Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.4934. Min Act: -0.1700
Data Index: 7268353 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.3059. Min Act: -0.1700
Data Index: 2936809 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.3059. Min Act: -0.1700
Data Index: 7571649 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.2121. Min Act: -0.1700
Data Index: 308981 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.2434. Min Act: -0.1700
Data Index: 2761776 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.2121. Min Act: -0.1700
Data Index: 1470682 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3120226 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.2121. Min Act: -0.1700
Data Index: 556809 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.1809. Min Act: -0.1700
Data Index: 7751050 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.1809. Min Act: -0.1700
Data Index: 7353188 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5633524 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.1809. Min Act: -0.1700
Data Index: 2975055 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.1496. Min Act: -0.1700
Data Index: 176328 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.0871. Min Act: -0.1700
Data Index: 1811469 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.0871. Min Act: -0.1700
Data Index: 6960213 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.0246. Min Act: -0.1700
Data Index: 266056 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4934. Min Range: -6.4934
Max Act: 6.0246. Min Act: -0.1700
Data Index: 1168309 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4934. Min Range: -6.4934
Max Act: 5.9934. Min Act: -0.1700
Data Index: 2697211 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4934. Min Range: -6.4934
Max Act: 5.9621. Min Act: -0.1700
Data Index: 7325109 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4934. Min Range: -6.4934
Max Act: 5.9621. Min Act: -0.1700
Data Index: 6029592 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19