Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2338 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8968. Min Act: -0.1700
Data Index: 4419382 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.8343. Min Act: -0.1700
Data Index: 3753207 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6781. Min Act: -0.1700
Data Index: 5066161 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6781. Min Act: -0.1700
Data Index: 4622986 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6468. Min Act: -0.1700
Data Index: 5168750 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6468. Min Act: -0.1700
Data Index: 4762567 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6156. Min Act: -0.1700
Data Index: 358210 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.6156. Min Act: -0.1700
Data Index: 5906329 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5843. Min Act: -0.1700
Data Index: 6143668 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5531. Min Act: -0.1700
Data Index: 336327 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5218. Min Act: -0.1700
Data Index: 4101404 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5218. Min Act: -0.1700
Data Index: 2692947 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5218. Min Act: -0.1700
Data Index: 5612319 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.5218. Min Act: -0.1700
Data Index: 4131880 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4906. Min Act: -0.1700
Data Index: 5602163 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4906. Min Act: -0.1700
Data Index: 6438518 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4593. Min Act: -0.1700
Data Index: 7814031 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4906. Min Act: -0.1700
Data Index: 5305115 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4906. Min Act: -0.1700
Data Index: 8089964 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8968. Min Range: -4.8968
Max Act: 4.4906. Min Act: -0.1700
Data Index: 3651159 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19