Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.4100. Min Act: -0.1700
Data Index: 1880498 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3787. Min Act: -0.1700
Data Index: 4024022 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 2821162 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 6893857 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 5091045 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.3162. Min Act: -0.1700
Data Index: 414156 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 6085846 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.2537. Min Act: -0.1700
Data Index: 3725282 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 7762143 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1912. Min Act: -0.1700
Data Index: 2100825 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1287. Min Act: -0.1700
Data Index: 2180108 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1287. Min Act: -0.1700
Data Index: 8012911 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1600. Min Act: -0.1700
Data Index: 805631 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.1287. Min Act: -0.1700
Data Index: 2755584 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0974. Min Act: -0.1700
Data Index: 2773148 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0662. Min Act: -0.1700
Data Index: 7295030 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0662. Min Act: -0.1700
Data Index: 2350574 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0662. Min Act: -0.1700
Data Index: 2934807 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0662. Min Act: -0.1700
Data Index: 1096120 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4100. Min Range: -4.4100
Max Act: 4.0974. Min Act: -0.1700
Data Index: 6169018 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19