Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.3571. Min Act: -0.1700
Data Index: 5645948 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.2629. Min Act: -0.1700
Data Index: 6617163 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.2000. Min Act: -0.1700
Data Index: 3566156 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1528. Min Act: -0.1700
Data Index: 3111425 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1371. Min Act: -0.1700
Data Index: 5014987 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1371. Min Act: -0.1700
Data Index: 34915 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1214. Min Act: -0.1700
Data Index: 4174463 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1214. Min Act: -0.1700
Data Index: 5929801 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1056. Min Act: -0.1700
Data Index: 4581291 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1056. Min Act: -0.1700
Data Index: 205890 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1214. Min Act: -0.1700
Data Index: 8609822 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1214. Min Act: -0.1700
Data Index: 302143 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1056. Min Act: -0.1700
Data Index: 6728188 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.0898. Min Act: -0.1700
Data Index: 5590735 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.0898. Min Act: -0.1700
Data Index: 613660 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1056. Min Act: -0.1700
Data Index: 8155984 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.0898. Min Act: -0.1700
Data Index: 3467786 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.0898. Min Act: -0.1700
Data Index: 4533405 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.1056. Min Act: -0.1700
Data Index: 6530906 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3571. Min Range: -3.3571
Max Act: 3.0583. Min Act: -0.1700
Data Index: 5394878 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19