Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1250 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2542. Min Range: -7.2542
Max Act: 7.2542. Min Act: -0.1700
Data Index: 3227841 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2542. Min Range: -7.2542
Max Act: 7.0354. Min Act: -0.1700
Data Index: 7735814 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2542. Min Range: -7.2542
Max Act: 7.0042. Min Act: -0.1700
Data Index: 848448 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9729. Min Act: -0.1700
Data Index: 7036968 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9729. Min Act: -0.1700
Data Index: 2339498 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2542. Min Range: -7.2542
Max Act: 7.0042. Min Act: -0.1700
Data Index: 889767 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2542. Min Range: -7.2542
Max Act: 7.0042. Min Act: -0.1700
Data Index: 4494153 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9417. Min Act: -0.1700
Data Index: 4206092 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9729. Min Act: -0.1700
Data Index: 8092596 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9417. Min Act: -0.1700
Data Index: 7519703 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9417. Min Act: -0.1700
Data Index: 2356767 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9417. Min Act: -0.1700
Data Index: 1312716 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.9417. Min Act: -0.1700
Data Index: 2271691 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8479. Min Act: -0.1700
Data Index: 6568037 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8479. Min Act: -0.1700
Data Index: 2044239 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8167. Min Act: -0.1700
Data Index: 5141521 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8479. Min Act: -0.1700
Data Index: 4605205 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8792. Min Act: -0.1700
Data Index: 974816 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8167. Min Act: -0.1700
Data Index: 5694979 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2542. Min Range: -7.2542
Max Act: 6.8792. Min Act: -0.1700
Data Index: 6707403 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19