Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.5907. Min Act: -0.1700
Data Index: 1534655 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 6830121 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4344. Min Act: -0.1700
Data Index: 6191028 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4344. Min Act: -0.1700
Data Index: 6275907 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4344. Min Act: -0.1700
Data Index: 2254635 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4032. Min Act: -0.1700
Data Index: 7554603 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4032. Min Act: -0.1700
Data Index: 5006836 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4032. Min Act: -0.1700
Data Index: 3873598 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.4032. Min Act: -0.1700
Data Index: 909450 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3719. Min Act: -0.1698
Data Index: 1000867 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3719. Min Act: -0.1700
Data Index: 4542421 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3719. Min Act: -0.1700
Data Index: 6360816 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3719. Min Act: -0.1700
Data Index: 6409454 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3719. Min Act: -0.1700
Data Index: 4911953 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 7228511 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 438777 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 7432836 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 4776935 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 208025 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5907. Min Range: -5.5907
Max Act: 5.3407. Min Act: -0.1700
Data Index: 5757357 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19