Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.9485. Min Act: -0.1700
Data Index: 2969157 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.9485. Min Act: -0.1700
Data Index: 5556186 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.8851. Min Act: -0.1700
Data Index: 8720739 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.8374. Min Act: -0.1700
Data Index: 8583679 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.8215. Min Act: -0.1700
Data Index: 5437785 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.8215. Min Act: -0.1700
Data Index: 6742388 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.8056. Min Act: -0.1700
Data Index: 7201298 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7897. Min Act: -0.1700
Data Index: 5700632 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7738. Min Act: -0.1700
Data Index: 2721906 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7897. Min Act: -0.1700
Data Index: 2933770 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7738. Min Act: -0.1700
Data Index: 7135522 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7897. Min Act: -0.1700
Data Index: 473925 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7738. Min Act: -0.1700
Data Index: 5658424 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7578. Min Act: -0.1700
Data Index: 835224 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7418. Min Act: -0.1700
Data Index: 5542067 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7259. Min Act: -0.1700
Data Index: 5130357 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7578. Min Act: -0.1700
Data Index: 3466954 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7099. Min Act: -0.1700
Data Index: 6184430 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.7099. Min Act: -0.1700
Data Index: 4178021 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9485. Min Range: -2.9485
Max Act: 2.6939. Min Act: -0.1700
Data Index: 3366225 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19