Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3770. Min Range: -6.3770
Max Act: 6.3770. Min Act: -0.1700
Data Index: 3511419 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3770. Min Range: -6.3770
Max Act: 6.0332. Min Act: -0.1700
Data Index: 2763564 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.9707. Min Act: -0.1700
Data Index: 2535232 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.9082. Min Act: -0.1699
Data Index: 5421420 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.8457. Min Act: -0.1700
Data Index: 6494580 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.8457. Min Act: -0.1700
Data Index: 4235031 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2250155 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.8145. Min Act: -0.1700
Data Index: 4543976 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.8145. Min Act: -0.1700
Data Index: 4036426 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7832. Min Act: -0.1700
Data Index: 6062957 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7832. Min Act: -0.1700
Data Index: 5421462 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7520. Min Act: -0.1700
Data Index: 7449554 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7520. Min Act: -0.1700
Data Index: 5600362 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7520. Min Act: -0.1700
Data Index: 617850 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7520. Min Act: -0.1700
Data Index: 7576110 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7207. Min Act: -0.1700
Data Index: 2717148 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7207. Min Act: -0.1700
Data Index: 2615949 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.6895. Min Act: -0.1700
Data Index: 1649703 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.6895. Min Act: -0.1700
Data Index: 1795966 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3770. Min Range: -6.3770
Max Act: 5.7207. Min Act: -0.1700
Data Index: 5972723 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19