Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.4279. Min Act: -0.1700
Data Index: 6328701 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.2310. Min Act: -0.1700
Data Index: 5312434 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.2144. Min Act: -0.1700
Data Index: 3708962 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.2144. Min Act: -0.1700
Data Index: 4415756 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1978. Min Act: -0.1700
Data Index: 6535452 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1978. Min Act: -0.1700
Data Index: 354832 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.2144. Min Act: -0.1700
Data Index: 3568661 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1812. Min Act: -0.1700
Data Index: 1150846 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1812. Min Act: -0.1700
Data Index: 5524980 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1646. Min Act: -0.1700
Data Index: 6167017 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1479. Min Act: -0.1700
Data Index: 6415349 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1700
Data Index: 8527923 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1145. Min Act: -0.1700
Data Index: 1236051 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1700
Data Index: 1573871 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1700
Data Index: 354790 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1700
Data Index: 5544224 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1696
Data Index: 354788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1479. Min Act: -0.1700
Data Index: 5378800 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1312. Min Act: -0.1700
Data Index: 3112241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4279. Min Range: -2.4279
Max Act: 2.1479. Min Act: -0.1700
Data Index: 712279 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19