Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.7734. Min Act: -0.1700
Data Index: 1191484 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.3672. Min Act: -0.1700
Data Index: 2988037 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.3047. Min Act: -0.1700
Data Index: 2384659 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.2422. Min Act: -0.1700
Data Index: 8066295 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.1797. Min Act: -0.1700
Data Index: 4486518 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.1484. Min Act: -0.1700
Data Index: 1908997 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.1484. Min Act: -0.1700
Data Index: 8393145 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7734. Min Range: -7.7734
Max Act: 7.1484. Min Act: -0.1700
Data Index: 541878 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.7422. Min Act: -0.1700
Data Index: 855825 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.7422. Min Act: -0.1700
Data Index: 3910815 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.7109. Min Act: -0.1700
Data Index: 2493537 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.6484. Min Act: -0.1700
Data Index: 7631516 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.5547. Min Act: -0.1700
Data Index: 3131150 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.5547. Min Act: -0.1700
Data Index: 2242624 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.4922. Min Act: -0.1700
Data Index: 327845 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.4922. Min Act: -0.1700
Data Index: 1968396 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.4609. Min Act: -0.1700
Data Index: 6620024 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.4297. Min Act: -0.1700
Data Index: 7752615 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.4297. Min Act: -0.1700
Data Index: 6361996 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7734. Min Range: -7.7734
Max Act: 6.3984. Min Act: -0.1700
Data Index: 5535451 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19