Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.2426. Min Act: -0.1700
Data Index: 3319726 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.1489. Min Act: -0.1700
Data Index: 8392761 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.1176. Min Act: -0.1700
Data Index: 6864017 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0551. Min Act: -0.1700
Data Index: 1325621 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 2414056 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 1209756 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 5694154 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 3990684 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.0935
Data Index: 1075718 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 4415766 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 139449 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 6360677 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 8216517 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 7858236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 3084219 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2426. Min Range: -5.2426
Max Act: 5.0239. Min Act: -0.1700
Data Index: 7201337 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 3645796 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9614. Min Act: -0.1700
Data Index: 522221 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9926. Min Act: -0.1700
Data Index: 3529500 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2426. Min Range: -5.2426
Max Act: 4.9614. Min Act: -0.1700
Data Index: 5730538 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19