Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4888 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1655509 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2507462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 7341833 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 4565747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 6173066 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 8326323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 3287100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2898851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 3645380 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 4324321 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 8787559 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 3620665 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 4266208 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.5377. Min Act: -0.1700
Data Index: 2832865 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.4752. Min Act: -0.1700
Data Index: 8289069 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.4127. Min Act: -0.1700
Data Index: 6146021 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.4127. Min Act: -0.1700
Data Index: 3971568 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.4127. Min Act: -0.1700
Data Index: 7740229 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.4439. Min Act: -0.1700
Data Index: 8289070 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5377. Min Range: -5.5377
Max Act: 5.3814. Min Act: -0.1700
Data Index: 3484150 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19