Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0980. Min Act: -0.1700
Data Index: 8338770 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0980. Min Act: -0.1700
Data Index: 7147210 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0355. Min Act: -0.1700
Data Index: 5950146 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0355. Min Act: -0.1700
Data Index: 1766570 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0355. Min Act: -0.1700
Data Index: 6549056 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0355. Min Act: -0.1700
Data Index: 4166636 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0980. Min Range: -9.0980
Max Act: 9.0355. Min Act: -0.1700
Data Index: 17552 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 17548 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 5968175 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 2087474 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 1499826 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 2764407 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 7759666 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9730. Min Act: -0.1700
Data Index: 7955260 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.8480. Min Act: -0.1700
Data Index: 7140399 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.8480. Min Act: -0.1700
Data Index: 8278597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9105. Min Act: -0.1700
Data Index: 7142450 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.9105. Min Act: -0.1700
Data Index: 163693 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.8480. Min Act: -0.1700
Data Index: 249594 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0980. Min Range: -9.0980
Max Act: 8.8480. Min Act: -0.1700
Data Index: 4019075 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19