Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1396 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.9738. Min Act: -0.1700
Data Index: 2474280 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.9113. Min Act: -0.1700
Data Index: 2654164 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.9425. Min Act: -0.1700
Data Index: 5233406 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.8800. Min Act: -0.1700
Data Index: 6462661 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.8800. Min Act: -0.1700
Data Index: 6803058 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7863. Min Act: -0.1700
Data Index: 3149466 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.8175. Min Act: -0.1700
Data Index: 5401597 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.8175. Min Act: -0.1700
Data Index: 5350836 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7863. Min Act: -0.1700
Data Index: 1231854 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7550. Min Act: -0.1700
Data Index: 7744106 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 3225585 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 4782327 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 921092 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 5398408 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 4447050 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 5407419 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.7238. Min Act: -0.1700
Data Index: 8504367 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.6925. Min Act: -0.1700
Data Index: 2295845 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.6925. Min Act: -0.1700
Data Index: 227510 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9738. Min Range: -4.9738
Max Act: 4.6613. Min Act: -0.1700
Data Index: 535606 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19