Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.2680. Min Act: -0.1700
Data Index: 4090601 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.1430. Min Act: -0.1700
Data Index: 7919290 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.1118. Min Act: -0.1700
Data Index: 4296828 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.1118. Min Act: -0.1700
Data Index: 5439316 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0493. Min Act: -0.1700
Data Index: 7075854 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0493. Min Act: -0.1700
Data Index: 5019154 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0180. Min Act: -0.1700
Data Index: 1230383 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0493. Min Act: -0.1700
Data Index: 3868200 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0493. Min Act: -0.1700
Data Index: 396161 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2680. Min Range: -7.2680
Max Act: 7.0493. Min Act: -0.1700
Data Index: 1037347 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9868. Min Act: -0.1700
Data Index: 8525314 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9868. Min Act: -0.1700
Data Index: 5021096 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9555. Min Act: -0.1700
Data Index: 5480760 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9555. Min Act: -0.1700
Data Index: 5675007 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9555. Min Act: -0.1700
Data Index: 2703183 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.9243. Min Act: -0.1700
Data Index: 628518 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.8930. Min Act: -0.1700
Data Index: 603432 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.8930. Min Act: -0.1700
Data Index: 2624612 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.8930. Min Act: -0.1700
Data Index: 8252188 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2680. Min Range: -7.2680
Max Act: 6.8930. Min Act: -0.1700
Data Index: 6307749 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19