Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.5301. Min Act: -0.1700
Data Index: 1531676 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.5301. Min Act: -0.1700
Data Index: 8573172 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.4676. Min Act: -0.1700
Data Index: 278321 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.4364. Min Act: -0.1700
Data Index: 1017554 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.4364. Min Act: -0.1700
Data Index: 636960 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3916453 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.3739. Min Act: -0.1700
Data Index: 3850856 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.3114. Min Act: -0.1700
Data Index: 2255909 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4258745 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2801. Min Act: -0.1700
Data Index: 1601231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.3114. Min Act: -0.1700
Data Index: 5257042 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2954687 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2801. Min Act: -0.1700
Data Index: 1290176 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2801. Min Act: -0.1700
Data Index: 2360876 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2801. Min Act: -0.1700
Data Index: 2691881 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2489. Min Act: -0.1700
Data Index: 6277314 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2801. Min Act: -0.1700
Data Index: 480523 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2176. Min Act: -0.1700
Data Index: 1648159 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2489. Min Act: -0.1700
Data Index: 4342450 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5301. Min Range: -5.5301
Max Act: 5.2489. Min Act: -0.1700
Data Index: 836052 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19