Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1705 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1958. Min Act: -0.1700
Data Index: 7592876 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1958. Min Act: -0.1700
Data Index: 1670953 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1792. Min Act: -0.1700
Data Index: 7313273 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1792. Min Act: -0.1700
Data Index: 7700983 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1459. Min Act: -0.1700
Data Index: 8308847 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1459. Min Act: -0.1700
Data Index: 8391043 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1626. Min Act: -0.1700
Data Index: 8009876 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1626. Min Act: -0.1697
Data Index: 6532970 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1292. Min Act: -0.1700
Data Index: 4344603 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1459. Min Act: -0.1700
Data Index: 7411544 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1958. Min Act: -0.1700
Data Index: 694214 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1626. Min Act: -0.1700
Data Index: 2484747 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1626. Min Act: -0.1700
Data Index: 7480632 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1459. Min Act: -0.1700
Data Index: 1502141 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1125. Min Act: -0.1700
Data Index: 6275024 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1459. Min Act: -0.1700
Data Index: 7250662 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1125. Min Act: -0.1700
Data Index: 6333907 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1125. Min Act: -0.1700
Data Index: 6345239 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1292. Min Act: -0.1700
Data Index: 4827923 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1958. Min Range: -2.1958
Max Act: 2.1125. Min Act: -0.1700
Data Index: 7167144 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19