Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3866. Min Range: -6.3866
Max Act: 6.3866. Min Act: -0.1700
Data Index: 7183366 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3866. Min Range: -6.3866
Max Act: 6.2928. Min Act: -0.1700
Data Index: 2326112 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3866. Min Range: -6.3866
Max Act: 6.2616. Min Act: -0.1700
Data Index: 5055883 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3866. Min Range: -6.3866
Max Act: 6.2303. Min Act: -0.1700
Data Index: 4545955 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3866. Min Range: -6.3866
Max Act: 6.1678. Min Act: -0.1700
Data Index: 2266754 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3908413 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.9803. Min Act: -0.1700
Data Index: 5019537 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.9178. Min Act: -0.1700
Data Index: 714197 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.9178. Min Act: -0.1700
Data Index: 5234386 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.8553. Min Act: -0.1700
Data Index: 4061110 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 8740828 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 8425565 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.8241. Min Act: -0.1700
Data Index: 1628443 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7928. Min Act: -0.1700
Data Index: 2231557 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7928. Min Act: -0.1700
Data Index: 2080478 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7616. Min Act: -0.1700
Data Index: 2740656 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7616. Min Act: -0.1700
Data Index: 7343862 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7616. Min Act: -0.1700
Data Index: 173535 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7616. Min Act: -0.1700
Data Index: 3298075 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3866. Min Range: -6.3866
Max Act: 5.7303. Min Act: -0.1700
Data Index: 6101224 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19