Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1559 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1892. Min Range: -6.1892
Max Act: 6.1892. Min Act: -0.1700
Data Index: 2152766 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.9705. Min Act: -0.1700
Data Index: 3431510 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.9392. Min Act: -0.1700
Data Index: 5342921 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.9392. Min Act: -0.1700
Data Index: 2096424 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.9080. Min Act: -0.1700
Data Index: 405880 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.9080. Min Act: -0.1700
Data Index: 233124 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8767. Min Act: -0.1700
Data Index: 4811224 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8767. Min Act: -0.1700
Data Index: 8446859 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8767. Min Act: -0.1700
Data Index: 2553084 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8142. Min Act: -0.1700
Data Index: 2589949 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8142. Min Act: -0.1700
Data Index: 8157789 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.8455. Min Act: -0.1700
Data Index: 8348992 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.7517. Min Act: -0.1700
Data Index: 5258094 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6676832 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 3335486 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 2651471 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 2944032 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.7205. Min Act: -0.1700
Data Index: 5642800 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6973341 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1892. Min Range: -6.1892
Max Act: 5.6892. Min Act: -0.1700
Data Index: 6264348 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19