Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3288 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.6642. Min Act: -0.1700
Data Index: 895103 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.3517. Min Act: -0.1700
Data Index: 1927457 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.3517. Min Act: -0.1700
Data Index: 3467728 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.2892. Min Act: -0.1699
Data Index: 7664007 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.1642. Min Act: -0.1700
Data Index: 2859847 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.1642. Min Act: -0.1700
Data Index: 6496162 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.1017. Min Act: -0.1700
Data Index: 6807711 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6642. Min Range: -9.6642
Max Act: 9.1017. Min Act: -0.1700
Data Index: 5704042 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.9142. Min Act: -0.1700
Data Index: 1755936 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.9142. Min Act: -0.1700
Data Index: 5302051 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.9142. Min Act: -0.1700
Data Index: 8238289 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.9142. Min Act: -0.1700
Data Index: 2212022 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.8517. Min Act: -0.1700
Data Index: 6848430 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7892. Min Act: -0.1700
Data Index: 4373044 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7892. Min Act: -0.1700
Data Index: 3671312 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7892. Min Act: -0.1700
Data Index: 5633391 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7267. Min Act: -0.1700
Data Index: 6162759 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7267. Min Act: -0.1700
Data Index: 2700453 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7267. Min Act: -0.1700
Data Index: 750719 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6642. Min Range: -9.6642
Max Act: 8.7267. Min Act: -0.1700
Data Index: 8235094 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19