Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2259 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0592. Min Act: -0.1699
Data Index: 216813 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0244. Min Act: -0.1689
Data Index: 3644167 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0244. Min Act: -0.1700
Data Index: 7294430 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0157. Min Act: -0.1694
Data Index: 7463823 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0157. Min Act: -0.1694
Data Index: 1279454 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0070. Min Act: -0.1700
Data Index: 5424625 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0157. Min Act: -0.1656
Data Index: 8653955 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0070. Min Act: -0.1697
Data Index: 8576088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0157. Min Act: -0.1695
Data Index: 783436 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9983. Min Act: -0.1689
Data Index: 1628818 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9983. Min Act: -0.1700
Data Index: 2805736 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9983. Min Act: -0.1700
Data Index: 8049539 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0592. Min Range: -1.0592
Max Act: 1.0070. Min Act: -0.1578
Data Index: 7177628 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9810. Min Act: -0.1700
Data Index: 2018818 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9896. Min Act: -0.1700
Data Index: 2737048 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9896. Min Act: -0.1699
Data Index: 1840173 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9983. Min Act: -0.1695
Data Index: 4980362 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9896. Min Act: -0.1698
Data Index: 1662596 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9896. Min Act: -0.1682
Data Index: 6905958 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0592. Min Range: -1.0592
Max Act: 0.9810. Min Act: -0.1700
Data Index: 2911600 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19