Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2234 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.5114. Min Act: -0.1700
Data Index: 3918054 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.5114. Min Act: -0.1700
Data Index: 6681727 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.5026. Min Act: -0.1700
Data Index: 7558395 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.5026. Min Act: -0.1700
Data Index: 7991648 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.5114. Min Act: -0.1700
Data Index: 8055909 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4938. Min Act: -0.1700
Data Index: 4028974 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4850. Min Act: -0.1700
Data Index: 1471292 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4762. Min Act: -0.1700
Data Index: 5551435 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4762. Min Act: -0.1700
Data Index: 8742023 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4762. Min Act: -0.1700
Data Index: 7419253 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4675. Min Act: -0.1700
Data Index: 461666 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4675. Min Act: -0.1700
Data Index: 4096860 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4675. Min Act: -0.1700
Data Index: 8482425 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4675. Min Act: -0.1700
Data Index: 2321499 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4675. Min Act: -0.1700
Data Index: 5733872 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4762. Min Act: -0.1700
Data Index: 6035078 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4587. Min Act: -0.1700
Data Index: 4900352 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4587. Min Act: -0.1700
Data Index: 7523693 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4411. Min Act: -0.1700
Data Index: 2769320 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5114. Min Range: -1.5114
Max Act: 1.4411. Min Act: -0.1700
Data Index: 213957 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19