Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.7168. Min Act: -0.1700
Data Index: 4055898 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4356. Min Act: -0.1700
Data Index: 1391502 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.4043. Min Act: -0.1700
Data Index: 5513226 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3418. Min Act: -0.1700
Data Index: 5350775 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.3418. Min Act: -0.1700
Data Index: 3297413 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2793. Min Act: -0.1700
Data Index: 7492334 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2793. Min Act: -0.1700
Data Index: 1472483 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2481. Min Act: -0.1700
Data Index: 8563506 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2481. Min Act: -0.1700
Data Index: 1714249 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2481. Min Act: -0.1700
Data Index: 1408616 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2481. Min Act: -0.1700
Data Index: 6031050 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2481. Min Act: -0.1700
Data Index: 2978311 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2168. Min Act: -0.1700
Data Index: 8299665 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2168. Min Act: -0.1700
Data Index: 2749092 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.2168. Min Act: -0.1700
Data Index: 5328116 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.1856. Min Act: -0.1700
Data Index: 4237993 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.1543. Min Act: -0.1700
Data Index: 1854262 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.1231. Min Act: -0.1700
Data Index: 5489319 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.0918. Min Act: -0.1700
Data Index: 1795282 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7168. Min Range: -5.7168
Max Act: 5.0918. Min Act: -0.1700
Data Index: 3553028 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19