Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.7315. Min Act: -0.1700
Data Index: 3355390 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.7158. Min Act: -0.1700
Data Index: 6450816 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.6063. Min Act: -0.1700
Data Index: 6708033 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5906. Min Act: -0.1700
Data Index: 7352793 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5906. Min Act: -0.1700
Data Index: 4163936 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5906. Min Act: -0.1700
Data Index: 1176173 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5750. Min Act: -0.1700
Data Index: 177785 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5750. Min Act: -0.1700
Data Index: 7583943 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5593. Min Act: -0.1700
Data Index: 1911126 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5280. Min Act: -0.1700
Data Index: 5869416 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5280. Min Act: -0.1700
Data Index: 4151976 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5280. Min Act: -0.1700
Data Index: 7824438 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5561904 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5280. Min Act: -0.1700
Data Index: 4333503 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5280. Min Act: -0.1700
Data Index: 1655375 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.4810. Min Act: -0.1700
Data Index: 7886306 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.5124. Min Act: -0.1700
Data Index: 5020398 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.4810. Min Act: -0.1700
Data Index: 2274090 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.4967. Min Act: -0.1700
Data Index: 1333520 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7315. Min Range: -3.7315
Max Act: 3.4810. Min Act: -0.1700
Data Index: 6191953 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19