Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4160 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.7118. Min Act: -0.1700
Data Index: 34023 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.5866. Min Act: -0.1700
Data Index: 4699414 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.5396. Min Act: -0.1700
Data Index: 5968016 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.5083. Min Act: -0.1700
Data Index: 6843240 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.5240. Min Act: -0.1700
Data Index: 2069662 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4927. Min Act: -0.1700
Data Index: 7070350 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4613. Min Act: -0.1700
Data Index: 969464 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4300. Min Act: -0.1700
Data Index: 89418 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4457. Min Act: -0.1700
Data Index: 5967944 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4300. Min Act: -0.1700
Data Index: 641142 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4143. Min Act: -0.1700
Data Index: 5135755 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4300. Min Act: -0.1700
Data Index: 181520 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4300. Min Act: -0.1700
Data Index: 2024981 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4143. Min Act: -0.1700
Data Index: 1351943 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.4143. Min Act: -0.1700
Data Index: 3816858 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.3830. Min Act: -0.1700
Data Index: 5023277 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.3986. Min Act: -0.1700
Data Index: 6793235 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.3830. Min Act: -0.1700
Data Index: 351835 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.3830. Min Act: -0.1700
Data Index: 2838789 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7118. Min Range: -3.7118
Max Act: 3.3986. Min Act: -0.1700
Data Index: 4722206 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19