Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4328. Min Act: -0.1700
Data Index: 1633750 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4491. Min Act: -0.1700
Data Index: 2217851 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4165. Min Act: -0.1700
Data Index: 477535 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4328. Min Act: -0.1700
Data Index: 4789256 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4002. Min Act: -0.1700
Data Index: 3500002 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.4002. Min Act: -0.1700
Data Index: 3781165 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3839. Min Act: -0.1700
Data Index: 2164896 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 2231432 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3839. Min Act: -0.1700
Data Index: 3346373 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 8260451 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 2860204 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 7968480 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 2300032 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3839. Min Act: -0.1700
Data Index: 6498826 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 6185920 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3511. Min Act: -0.1700
Data Index: 6243574 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3675. Min Act: -0.1700
Data Index: 4841490 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3511. Min Act: -0.1700
Data Index: 2239140 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3511. Min Act: -0.1700
Data Index: 573776 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4491. Min Range: -2.4491
Max Act: 2.3511. Min Act: -0.1700
Data Index: 6279077 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19