Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.3220. Min Act: -0.1700
Data Index: 6620542 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.2595. Min Act: -0.1700
Data Index: 3911973 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.2283. Min Act: -0.1700
Data Index: 885253 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1970. Min Act: -0.1700
Data Index: 6110317 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7619545 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1658. Min Act: -0.1700
Data Index: 7347720 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1658. Min Act: -0.1700
Data Index: 4686482 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 1925169 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 5500244 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 2645158 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 8007307 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 1805774 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 7432587 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.1033. Min Act: -0.1700
Data Index: 7741693 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 1739855 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 2904672 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 311714 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 342613 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 8337040 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3220. Min Range: -5.3220
Max Act: 5.0720. Min Act: -0.1700
Data Index: 3588898 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19