Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.6164. Min Act: -0.1698
Data Index: 4588370 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.5851. Min Act: -0.1700
Data Index: 2203329 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.5226. Min Act: -0.1700
Data Index: 8284162 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.4289. Min Act: -0.1700
Data Index: 921920 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.4601. Min Act: -0.1700
Data Index: 8508726 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 4581383 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5652418 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5017838 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3976. Min Act: -0.1700
Data Index: 5097435 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3351. Min Act: -0.1700
Data Index: 3922131 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3351. Min Act: -0.1700
Data Index: 1160264 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 3167087 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3351. Min Act: -0.1700
Data Index: 4814688 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3351. Min Act: -0.1700
Data Index: 921930 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3351. Min Act: -0.1700
Data Index: 2862560 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 3011741 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 4579989 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 5086376 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.3039. Min Act: -0.1700
Data Index: 6472691 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6164. Min Range: -4.6164
Max Act: 4.2414. Min Act: -0.1700
Data Index: 5045954 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19