Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.9354. Min Act: -0.1700
Data Index: 7974510 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.8417. Min Act: -0.1700
Data Index: 1178737 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.8417. Min Act: -0.1700
Data Index: 5819643 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.7792. Min Act: -0.1700
Data Index: 4409163 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6719417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.7167. Min Act: -0.1700
Data Index: 2326179 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.7167. Min Act: -0.1700
Data Index: 6084541 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6854. Min Act: -0.1700
Data Index: 6205491 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6854. Min Act: -0.1700
Data Index: 8486682 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6854. Min Act: -0.1700
Data Index: 4050008 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6542. Min Act: -0.1700
Data Index: 8695018 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6542. Min Act: -0.1700
Data Index: 2736943 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6229. Min Act: -0.1700
Data Index: 8788545 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6229. Min Act: -0.1700
Data Index: 6828834 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6229. Min Act: -0.1700
Data Index: 2161744 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6542. Min Act: -0.1700
Data Index: 1967911 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6229. Min Act: -0.1700
Data Index: 4957512 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4495436 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.5917. Min Act: -0.1700
Data Index: 3054735 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9354. Min Range: -5.9354
Max Act: 5.5917. Min Act: -0.1700
Data Index: 8358965 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19