Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2103 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1151. Min Range: -7.1151
Max Act: 7.1151. Min Act: -0.1700
Data Index: 5262906 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.9901. Min Act: -0.1700
Data Index: 8096811 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.8964. Min Act: -0.1700
Data Index: 6729913 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.8339. Min Act: -0.1700
Data Index: 4810584 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.7714. Min Act: -0.1700
Data Index: 2005936 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.7714. Min Act: -0.1700
Data Index: 4482393 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.7089. Min Act: -0.1700
Data Index: 1883665 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.6776. Min Act: -0.1700
Data Index: 5768457 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.6151. Min Act: -0.1700
Data Index: 4134720 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.5839. Min Act: -0.1700
Data Index: 4758574 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.5526. Min Act: -0.1700
Data Index: 5287180 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.5214. Min Act: -0.1700
Data Index: 571173 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.4901. Min Act: -0.1700
Data Index: 135638 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3964. Min Act: -0.1700
Data Index: 1030644 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3651. Min Act: -0.1700
Data Index: 6285032 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3651. Min Act: -0.1700
Data Index: 2068509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3651. Min Act: -0.1700
Data Index: 4050323 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3339. Min Act: -0.1700
Data Index: 2426602 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3026. Min Act: -0.1700
Data Index: 2601405 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1151. Min Range: -7.1151
Max Act: 6.3026. Min Act: -0.1700
Data Index: 2667973 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19