Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3952 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.9095. Min Act: -0.1700
Data Index: 5530043 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.8470. Min Act: -0.1700
Data Index: 3999181 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.8157. Min Act: -0.1700
Data Index: 1670756 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.7532. Min Act: -0.1700
Data Index: 229406 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.7845. Min Act: -0.1700
Data Index: 6034185 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.6595. Min Act: -0.1700
Data Index: 5227360 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.5970. Min Act: -0.1700
Data Index: 6272179 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.5345. Min Act: -0.1700
Data Index: 3202033 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.5032. Min Act: -0.1700
Data Index: 7496652 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4720. Min Act: -0.1700
Data Index: 7745125 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4720. Min Act: -0.1700
Data Index: 3850181 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4720. Min Act: -0.1700
Data Index: 7806649 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4407. Min Act: -0.1700
Data Index: 5508231 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4095. Min Act: -0.1700
Data Index: 3499826 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.4095. Min Act: -0.1700
Data Index: 4322455 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.3470. Min Act: -0.1700
Data Index: 1234476 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.3470. Min Act: -0.1700
Data Index: 959558 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.3470. Min Act: -0.1700
Data Index: 134632 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.3157. Min Act: -0.1700
Data Index: 6896270 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9095. Min Range: -6.9095
Max Act: 6.3157. Min Act: -0.1700
Data Index: 1050080 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19