Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4347 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0006. Min Range: -9.0006
Max Act: 9.0006. Min Act: -0.1700
Data Index: 8023267 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.8131. Min Act: -0.1700
Data Index: 6396739 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.5631. Min Act: -0.1700
Data Index: 7150634 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.3131. Min Act: -0.1700
Data Index: 2589708 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.3756. Min Act: -0.1700
Data Index: 8196308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.3131. Min Act: -0.1700
Data Index: 5298892 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.2506. Min Act: -0.1700
Data Index: 8484221 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.2506. Min Act: -0.1700
Data Index: 5961264 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0943. Min Act: -0.1700
Data Index: 4127174 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0943. Min Act: -0.1700
Data Index: 5046643 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 2533751 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 6875363 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 2289683 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0318. Min Act: -0.1700
Data Index: 3448118 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0006. Min Range: -9.0006
Max Act: 7.9693. Min Act: -0.1700
Data Index: 7142768 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0006. Min Range: -9.0006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 8106920 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0006. Min Range: -9.0006
Max Act: 7.9381. Min Act: -0.1700
Data Index: 4942371 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0006. Min Range: -9.0006
Max Act: 7.9381. Min Act: -0.1700
Data Index: 1261327 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0006. Min Range: -9.0006
Max Act: 7.9068. Min Act: -0.1700
Data Index: 3997836 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0006. Min Range: -9.0006
Max Act: 7.8756. Min Act: -0.1700
Data Index: 3532328 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19