Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.8526. Min Act: -0.1700
Data Index: 7589314 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.7589. Min Act: -0.1700
Data Index: 4770039 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.7589. Min Act: -0.1700
Data Index: 1358450 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6651. Min Act: -0.1700
Data Index: 8490406 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6651. Min Act: -0.1700
Data Index: 7279613 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6651. Min Act: -0.1700
Data Index: 597410 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6964. Min Act: -0.1700
Data Index: 8393006 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6026. Min Act: -0.1700
Data Index: 4986561 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6026. Min Act: -0.1700
Data Index: 3232117 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6026. Min Act: -0.1700
Data Index: 4145798 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.6026. Min Act: -0.1700
Data Index: 3411511 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5714. Min Act: -0.1700
Data Index: 2505998 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5714. Min Act: -0.1700
Data Index: 1428974 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5401. Min Act: -0.1700
Data Index: 8475047 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5714. Min Act: -0.1700
Data Index: 3015766 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5089. Min Act: -0.1700
Data Index: 8303902 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5089. Min Act: -0.1700
Data Index: 1308687 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.4776. Min Act: -0.1700
Data Index: 6924755 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5401. Min Act: -0.1700
Data Index: 2385368 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8526. Min Range: -6.8526
Max Act: 6.5089. Min Act: -0.1700
Data Index: 4101631 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19