Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4127 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.6329. Min Act: -0.1700
Data Index: 8559335 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.5233. Min Act: -0.1700
Data Index: 5833104 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.4764. Min Act: -0.1700
Data Index: 5833105 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.2568. Min Act: -0.1700
Data Index: 2960488 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.2096. Min Act: -0.1700
Data Index: 5553947 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.2096. Min Act: -0.1700
Data Index: 1616939 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.2096. Min Act: -0.1700
Data Index: 3611781 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.2096. Min Act: -0.1700
Data Index: 3287067 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1939. Min Act: -0.1700
Data Index: 4407573 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1939. Min Act: -0.1700
Data Index: 1056864 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1939. Min Act: -0.1700
Data Index: 1069850 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1939. Min Act: -0.1700
Data Index: 4890010 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1781. Min Act: -0.1700
Data Index: 6795182 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1781. Min Act: -0.1700
Data Index: 3211324 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1781. Min Act: -0.1700
Data Index: 4407572 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1624. Min Act: -0.1700
Data Index: 4407574 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1624. Min Act: -0.1700
Data Index: 2069286 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1467. Min Act: -0.1700
Data Index: 5677409 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1467. Min Act: -0.1700
Data Index: 6081404 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6329. Min Range: -3.6329
Max Act: 3.1309. Min Act: -0.1700
Data Index: 3287073 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19