Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1523. Min Act: 0.0821
Data Index: 6187341 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1489
Data Index: 1204428 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0247
Data Index: 8408958 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0399
Data Index: 6201369 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1529
Data Index: 3335130 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1251
Data Index: 5534618 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1555
Data Index: 3893810 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0698
Data Index: 2818969 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0161
Data Index: 5352364 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1698
Data Index: 2279241 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1218
Data Index: 997762 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1359
Data Index: 4521456 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: 0.0552
Data Index: 4412656 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0683
Data Index: 7430810 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.1331
Data Index: 1935519 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0067
Data Index: 4034142 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: 0.0068
Data Index: 1762483 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.1051. Min Act: -0.0429
Data Index: 4010564 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.0736. Min Act: -0.1535
Data Index: 1399802 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1523. Min Range: -3.1523
Max Act: 3.0104. Min Act: 0.0746
Data Index: 3481230 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19