Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4775. Min Act: -0.1700
Data Index: 3282107 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4305. Min Act: -0.1700
Data Index: 3295688 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4305. Min Act: -0.1700
Data Index: 6535103 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4305. Min Act: -0.1700
Data Index: 8389971 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4149. Min Act: -0.1700
Data Index: 214020 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.4149. Min Act: -0.1700
Data Index: 6486022 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3835. Min Act: -0.1700
Data Index: 7966139 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3521. Min Act: -0.1700
Data Index: 3487931 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3678. Min Act: -0.1700
Data Index: 7667292 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3678. Min Act: -0.1700
Data Index: 5494333 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3364. Min Act: -0.1700
Data Index: 2558257 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3364. Min Act: -0.1700
Data Index: 1969264 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3364. Min Act: -0.1700
Data Index: 6914066 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3208. Min Act: -0.1700
Data Index: 2240609 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3051. Min Act: -0.1700
Data Index: 753699 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3208. Min Act: -0.1700
Data Index: 3212450 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2894. Min Act: -0.1700
Data Index: 5238377 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.3051. Min Act: -0.1700
Data Index: 5140684 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2580. Min Act: -0.1700
Data Index: 5564422 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4775. Min Range: -3.4775
Max Act: 3.2737. Min Act: -0.1700
Data Index: 2512977 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19