Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1663. Min Range: -7.1663
Max Act: 7.1663. Min Act: -0.1700
Data Index: 2290916 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1663. Min Range: -7.1663
Max Act: 7.0101. Min Act: -0.1700
Data Index: 7656543 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.9163. Min Act: -0.1700
Data Index: 1963543 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.9476. Min Act: -0.1700
Data Index: 8350683 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.8851. Min Act: -0.1700
Data Index: 7535033 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.8538. Min Act: -0.1700
Data Index: 8701675 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.7913. Min Act: -0.1700
Data Index: 676063 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.7913. Min Act: -0.1700
Data Index: 519250 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.6351. Min Act: -0.1700
Data Index: 5458758 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.6038. Min Act: -0.1700
Data Index: 1473460 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.5726. Min Act: -0.1700
Data Index: 6529919 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.5726. Min Act: -0.1700
Data Index: 579105 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.5413. Min Act: -0.1700
Data Index: 1503789 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.5726. Min Act: -0.1700
Data Index: 5587737 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.5101. Min Act: -0.1700
Data Index: 1803458 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.4788. Min Act: -0.1700
Data Index: 4014432 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.4163. Min Act: -0.1700
Data Index: 2290923 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.4476. Min Act: -0.1700
Data Index: 8813673 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.4476. Min Act: -0.1700
Data Index: 2563622 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1663. Min Range: -7.1663
Max Act: 6.4163. Min Act: -0.1700
Data Index: 6996873 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19