Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.5132. Min Act: -0.1700
Data Index: 8831285 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.2632. Min Act: -0.1700
Data Index: 1365520 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.1382. Min Act: -0.1699
Data Index: 6766629 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.0757. Min Act: -0.1700
Data Index: 5652283 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.0132. Min Act: -0.1700
Data Index: 6706798 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.0132. Min Act: -0.1700
Data Index: 7541719 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5132. Min Range: -8.5132
Max Act: 8.0132. Min Act: -0.1700
Data Index: 8660711 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.9507. Min Act: -0.1700
Data Index: 8201077 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.9507. Min Act: -0.1700
Data Index: 6574132 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8882. Min Act: -0.1700
Data Index: 2362187 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8882. Min Act: -0.1700
Data Index: 8714920 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 2878457 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 3717336 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 4272424 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 7617225 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8257. Min Act: -0.1700
Data Index: 2600740 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.8882. Min Act: -0.1700
Data Index: 7002134 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.7632. Min Act: -0.1700
Data Index: 1261007 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.7632. Min Act: -0.1700
Data Index: 4139854 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5132. Min Range: -8.5132
Max Act: 7.7632. Min Act: -0.1700
Data Index: 8704378 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19