Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4265 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.2833. Min Act: -0.1700
Data Index: 2818131 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.2520. Min Act: -0.1700
Data Index: 8155320 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.2520. Min Act: -0.1700
Data Index: 2763712 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.1583. Min Act: -0.1700
Data Index: 3319445 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.1895. Min Act: -0.1700
Data Index: 5211778 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.1583. Min Act: -0.1700
Data Index: 6361481 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.1270. Min Act: -0.1700
Data Index: 6325061 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0645. Min Act: -0.1700
Data Index: 203641 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0958. Min Act: -0.1700
Data Index: 8584145 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0645. Min Act: -0.1700
Data Index: 7317655 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0645. Min Act: -0.1700
Data Index: 4960953 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0333. Min Act: -0.1700
Data Index: 3491604 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0020. Min Act: -0.1700
Data Index: 4311210 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0333. Min Act: -0.1700
Data Index: 1606709 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0333. Min Act: -0.1700
Data Index: 4636885 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0020. Min Act: -0.1700
Data Index: 7122389 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2833. Min Range: -7.2833
Max Act: 7.0020. Min Act: -0.1700
Data Index: 2755780 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2833. Min Range: -7.2833
Max Act: 6.9708. Min Act: -0.1700
Data Index: 990274 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2833. Min Range: -7.2833
Max Act: 6.9708. Min Act: -0.1700
Data Index: 3646718 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2833. Min Range: -7.2833
Max Act: 6.9708. Min Act: -0.1700
Data Index: 1608895 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19