Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1976 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.9135. Min Act: -0.1700
Data Index: 1230068 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.6946. Min Act: -0.1700
Data Index: 7488379 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.6477. Min Act: -0.1700
Data Index: 3741789 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.6633. Min Act: -0.1700
Data Index: 4871704 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.6007. Min Act: -0.1700
Data Index: 557388 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.5538. Min Act: -0.1700
Data Index: 4689289 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.5381. Min Act: -0.1700
Data Index: 8021905 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.5224. Min Act: -0.1700
Data Index: 8500312 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.5068. Min Act: -0.1700
Data Index: 7683148 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.5068. Min Act: -0.1700
Data Index: 954723 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4754. Min Act: -0.1700
Data Index: 7501376 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4598. Min Act: -0.1700
Data Index: 2357967 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4441. Min Act: -0.1700
Data Index: 1378318 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4441. Min Act: -0.1700
Data Index: 3366416 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 7071249 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 3629416 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 5050913 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 107658 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 4413217 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9135. Min Range: -3.9135
Max Act: 3.4128. Min Act: -0.1700
Data Index: 2675899 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19