Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.7803. Min Act: -0.1700
Data Index: 7779617 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.6553. Min Act: -0.1700
Data Index: 6836307 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.3741. Min Act: -0.1700
Data Index: 1290260 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.3428. Min Act: -0.1700
Data Index: 2042670 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.3428. Min Act: -0.1700
Data Index: 8201069 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.3116. Min Act: -0.1700
Data Index: 5846723 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.2803. Min Act: -0.1700
Data Index: 4024884 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.2491. Min Act: -0.1700
Data Index: 7151858 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.2178. Min Act: -0.1700
Data Index: 4476960 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 6067273 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 3724292 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 8719580 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 4758933 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 1273936 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 2944417 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1553. Min Act: -0.1700
Data Index: 4196206 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 3904022 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 5278102 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.1241. Min Act: -0.1700
Data Index: 8147505 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7803. Min Range: -7.7803
Max Act: 7.0928. Min Act: -0.1700
Data Index: 4852548 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19