Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 346 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5823. Min Range: -7.5823
Max Act: 7.5823. Min Act: -0.1700
Data Index: 673704 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5823. Min Range: -7.5823
Max Act: 7.3010. Min Act: -0.1700
Data Index: 7426774 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5823. Min Range: -7.5823
Max Act: 7.0510. Min Act: -0.1700
Data Index: 5230321 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9885. Min Act: -0.1700
Data Index: 4770100 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9573. Min Act: -0.1700
Data Index: 3501750 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9885. Min Act: -0.1700
Data Index: 2321263 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9260. Min Act: -0.1700
Data Index: 5947608 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8948. Min Act: -0.1700
Data Index: 8061986 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.9260. Min Act: -0.1700
Data Index: 4576105 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8323. Min Act: -0.1700
Data Index: 5125471 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8323. Min Act: -0.1700
Data Index: 4642033 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7385. Min Act: -0.1700
Data Index: 167021 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8010. Min Act: -0.1700
Data Index: 8404870 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.8323. Min Act: -0.1700
Data Index: 8551438 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 5125488 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 3833904 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7385. Min Act: -0.1700
Data Index: 237806 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7698. Min Act: -0.1700
Data Index: 8022203 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.7073. Min Act: -0.1700
Data Index: 8391863 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5823. Min Range: -7.5823
Max Act: 6.6760. Min Act: -0.1700
Data Index: 396142 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19