Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3151730 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.8806. Min Act: -0.1700
Data Index: 465616 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.6931. Min Act: -0.1700
Data Index: 3357009 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5994. Min Act: -0.1700
Data Index: 1640803 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5681. Min Act: -0.1700
Data Index: 3289569 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5994. Min Act: -0.1700
Data Index: 2971981 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5056. Min Act: -0.1700
Data Index: 1018836 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5369. Min Act: -0.1700
Data Index: 2066725 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4744. Min Act: -0.1700
Data Index: 1778769 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4744. Min Act: -0.1700
Data Index: 4849585 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.5369. Min Act: -0.1700
Data Index: 6558048 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4744. Min Act: -0.1700
Data Index: 107687 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4431. Min Act: -0.1700
Data Index: 1389876 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4431. Min Act: -0.1700
Data Index: 7443032 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4431. Min Act: -0.1700
Data Index: 535694 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5150791 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4119. Min Act: -0.1700
Data Index: 5288268 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.3806. Min Act: -0.1700
Data Index: 337466 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4119. Min Act: -0.1700
Data Index: 70378 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9744. Min Range: -5.9744
Max Act: 5.4119. Min Act: -0.1700
Data Index: 4833278 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19