Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0114. Min Range: -5.0114
Max Act: 5.0114. Min Act: -0.1700
Data Index: 6264890 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.9801. Min Act: -0.1700
Data Index: 7551692 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.9489. Min Act: -0.1700
Data Index: 3888134 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.9176. Min Act: -0.1700
Data Index: 1101421 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.9176. Min Act: -0.1700
Data Index: 4622219 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.8864. Min Act: -0.1700
Data Index: 3367445 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.8864. Min Act: -0.1700
Data Index: 4547538 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.7926. Min Act: -0.1700
Data Index: 3084492 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.7614. Min Act: -0.1700
Data Index: 246726 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.7614. Min Act: -0.1700
Data Index: 3229565 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.7301. Min Act: -0.1700
Data Index: 5827666 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6989. Min Act: -0.1700
Data Index: 7188 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6989. Min Act: -0.1700
Data Index: 5339331 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6364. Min Act: -0.1700
Data Index: 3092836 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 8287401 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6364. Min Act: -0.1700
Data Index: 1528490 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6676. Min Act: -0.1700
Data Index: 1042623 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 640359 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 2038490 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0114. Min Range: -5.0114
Max Act: 4.6051. Min Act: -0.1700
Data Index: 5660150 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19