Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.8252. Min Act: -0.1700
Data Index: 544763 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7615. Min Act: -0.1700
Data Index: 8357468 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7295. Min Act: -0.1700
Data Index: 8554584 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7615. Min Act: -0.1700
Data Index: 5204341 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7136. Min Act: -0.1700
Data Index: 1408804 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7136. Min Act: -0.1700
Data Index: 5686092 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7295. Min Act: -0.1700
Data Index: 1372378 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 4019674 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7136. Min Act: -0.1700
Data Index: 5303419 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7136. Min Act: -0.1700
Data Index: 8162072 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 8280288 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6815. Min Act: -0.1700
Data Index: 974363 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 8188389 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 5856872 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 2923110 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 8716777 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6815. Min Act: -0.1700
Data Index: 5742284 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.7136. Min Act: -0.1700
Data Index: 2268554 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 8555848 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8252. Min Range: -2.8252
Max Act: 2.6976. Min Act: -0.1700
Data Index: 863247 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19