Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.3043. Min Act: -0.1700
Data Index: 3521075 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.1720. Min Act: -0.1699
Data Index: 3963081 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.1220. Min Act: -0.1700
Data Index: 4150086 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.1053. Min Act: -0.1700
Data Index: 8280701 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.1053. Min Act: -0.1700
Data Index: 5526215 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1700
Data Index: 7712469 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0885. Min Act: -0.1700
Data Index: 2306754 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1699
Data Index: 3282824 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1700
Data Index: 2719733 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1700
Data Index: 1193868 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1699
Data Index: 7440413 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1699
Data Index: 8160131 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0885. Min Act: -0.1700
Data Index: 1443099 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0717. Min Act: -0.1700
Data Index: 8202285 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0549. Min Act: -0.1700
Data Index: 2605993 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0381. Min Act: -0.1700
Data Index: 7640976 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0549. Min Act: -0.1700
Data Index: 5104624 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0381. Min Act: -0.1700
Data Index: 8125681 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0381. Min Act: -0.1700
Data Index: 8074781 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3043. Min Range: -2.3043
Max Act: 2.0549. Min Act: -0.1700
Data Index: 7993926 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19