Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4649 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1512. Min Range: -3.1512
Max Act: 3.1512. Min Act: -0.1700
Data Index: 7693637 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1512. Min Range: -3.1512
Max Act: 3.0251. Min Act: -0.1700
Data Index: 1860192 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.9935. Min Act: -0.1700
Data Index: 259465 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.9461. Min Act: -0.1700
Data Index: 4396644 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.9461. Min Act: -0.1700
Data Index: 1511900 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.9461. Min Act: -0.1700
Data Index: 5356628 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.9144. Min Act: -0.1700
Data Index: 4716116 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8985. Min Act: -0.1700
Data Index: 2172967 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8827. Min Act: -0.1700
Data Index: 3457227 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8668. Min Act: -0.1700
Data Index: 6701766 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8668. Min Act: -0.1700
Data Index: 47079 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8509. Min Act: -0.1700
Data Index: 8145012 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8509. Min Act: -0.1700
Data Index: 6236233 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8509. Min Act: -0.1700
Data Index: 4371333 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8350. Min Act: -0.1700
Data Index: 7493712 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8350. Min Act: -0.1700
Data Index: 7498167 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8350. Min Act: -0.1700
Data Index: 290625 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8350. Min Act: -0.1700
Data Index: 5870687 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8350. Min Act: -0.1700
Data Index: 6715871 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1512. Min Range: -3.1512
Max Act: 2.8191. Min Act: -0.1700
Data Index: 2943638 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19