Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.9415. Min Act: -0.1700
Data Index: 8483739 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.7852. Min Act: -0.1700
Data Index: 2926210 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.5977. Min Act: -0.1700
Data Index: 5610117 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.4727. Min Act: -0.1700
Data Index: 8785998 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.4727. Min Act: -0.1700
Data Index: 2631574 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.4727. Min Act: -0.1700
Data Index: 4328521 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.4415. Min Act: -0.1700
Data Index: 5808236 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.2852. Min Act: -0.1700
Data Index: 250263 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.3790. Min Act: -0.1700
Data Index: 715933 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3334675 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.1915. Min Act: -0.1700
Data Index: 993966 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.1602. Min Act: -0.1700
Data Index: 5231266 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.1290. Min Act: -0.1700
Data Index: 5799673 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.0352. Min Act: -0.1700
Data Index: 1752321 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.0040. Min Act: -0.1700
Data Index: 2902199 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.0040. Min Act: -0.1700
Data Index: 6958656 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.0665. Min Act: -0.1700
Data Index: 5746506 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9415. Min Range: -6.9415
Max Act: 5.9727. Min Act: -0.1700
Data Index: 5342013 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9415. Min Range: -6.9415
Max Act: 5.9415. Min Act: -0.1700
Data Index: 2195486 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9415. Min Range: -6.9415
Max Act: 6.0040. Min Act: -0.1700
Data Index: 2167536 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19