Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.4237. Min Act: -0.1700
Data Index: 7225725 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.3612. Min Act: -0.1700
Data Index: 6402602 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 309125 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.3299. Min Act: -0.1700
Data Index: 1741828 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 3777752 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 427652 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 3216851 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 4144431 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2987. Min Act: -0.1700
Data Index: 2266215 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2674. Min Act: -0.1700
Data Index: 4478322 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2362. Min Act: -0.1700
Data Index: 6524154 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2362. Min Act: -0.1700
Data Index: 3372261 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2362. Min Act: -0.1700
Data Index: 8056479 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2362. Min Act: -0.1700
Data Index: 2018874 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2049. Min Act: -0.1700
Data Index: 7074873 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2362. Min Act: -0.1700
Data Index: 2667238 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2049. Min Act: -0.1700
Data Index: 1229912 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.1737. Min Act: -0.1700
Data Index: 3801914 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.1737. Min Act: -0.1700
Data Index: 2599826 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4237. Min Range: -5.4237
Max Act: 5.2049. Min Act: -0.1700
Data Index: 4641722 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19