Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.7093. Min Act: -0.1700
Data Index: 8446767 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.5218. Min Act: -0.1700
Data Index: 798405 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.5218. Min Act: -0.1700
Data Index: 43541 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4905. Min Act: -0.1700
Data Index: 5513583 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4905. Min Act: -0.1700
Data Index: 8756534 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4593. Min Act: -0.1700
Data Index: 8116021 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4593. Min Act: -0.1700
Data Index: 5270615 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4593. Min Act: -0.1700
Data Index: 4676500 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4593. Min Act: -0.1700
Data Index: 4048466 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.3968. Min Act: -0.1700
Data Index: 2057592 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4280. Min Act: -0.1700
Data Index: 8756535 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4593. Min Act: -0.1700
Data Index: 3151798 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4280. Min Act: -0.1700
Data Index: 798408 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4280. Min Act: -0.1700
Data Index: 1367209 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.3968. Min Act: -0.1700
Data Index: 5079238 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.3968. Min Act: -0.1700
Data Index: 6871892 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4280. Min Act: -0.1700
Data Index: 8756536 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.4280. Min Act: -0.1700
Data Index: 5270601 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.3655. Min Act: -0.1700
Data Index: 957464 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7093. Min Range: -4.7093
Max Act: 4.3343. Min Act: -0.1700
Data Index: 6983020 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19