Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3287 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.6525. Min Act: -0.1700
Data Index: 3930480 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5882. Min Act: -0.1700
Data Index: 7401608 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5398. Min Act: -0.1700
Data Index: 8696159 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5560. Min Act: -0.1700
Data Index: 1133435 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5560. Min Act: -0.1700
Data Index: 7027763 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5560. Min Act: -0.1700
Data Index: 3542214 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.5237. Min Act: -0.1700
Data Index: 7986472 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4913. Min Act: -0.1700
Data Index: 8065663 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4588. Min Act: -0.1700
Data Index: 6985441 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4751. Min Act: -0.1700
Data Index: 1566323 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1579239 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4426. Min Act: -0.1700
Data Index: 8122495 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4751. Min Act: -0.1700
Data Index: 3310990 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4751. Min Act: -0.1700
Data Index: 7856133 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4588. Min Act: -0.1700
Data Index: 2577295 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4263. Min Act: -0.1700
Data Index: 4289676 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4426. Min Act: -0.1700
Data Index: 2509154 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4426. Min Act: -0.1700
Data Index: 3277934 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4263. Min Act: -0.1700
Data Index: 5985634 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6525. Min Range: -2.6525
Max Act: 2.4263. Min Act: -0.1700
Data Index: 5413813 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19