Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1068 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3621. Min Range: -5.3621
Max Act: 5.3621. Min Act: -0.1700
Data Index: 3242719 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3621. Min Range: -5.3621
Max Act: 5.1121. Min Act: -0.1700
Data Index: 6399099 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3621. Min Range: -5.3621
Max Act: 5.0809. Min Act: -0.1700
Data Index: 6566244 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.9871. Min Act: -0.1700
Data Index: 2542922 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.9559. Min Act: -0.1700
Data Index: 151203 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8934. Min Act: -0.1700
Data Index: 6052004 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.9246. Min Act: -0.1700
Data Index: 4841269 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.9246. Min Act: -0.1700
Data Index: 892304 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7232278 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4609634 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7232277 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2868505 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.9246. Min Act: -0.1700
Data Index: 3408810 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 5732034 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2039766 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8309. Min Act: -0.1700
Data Index: 3544024 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 6506495 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 934135 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8621. Min Act: -0.1700
Data Index: 5096271 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3621. Min Range: -5.3621
Max Act: 4.8309. Min Act: -0.1700
Data Index: 416066 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19