Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2384 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0989. Min Range: -5.0989
Max Act: 5.0676. Min Act: -0.1700
Data Index: 8796005 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0989. Min Range: -5.0989
Max Act: 5.0989. Min Act: -0.1700
Data Index: 4165401 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0989. Min Range: -5.0989
Max Act: 5.0676. Min Act: -0.1700
Data Index: 5457325 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0989. Min Range: -5.0989
Max Act: 5.0364. Min Act: -0.1700
Data Index: 1849173 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0989. Min Range: -5.0989
Max Act: 5.0051. Min Act: -0.1700
Data Index: 2926644 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9739. Min Act: -0.1700
Data Index: 6224 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9739. Min Act: -0.1700
Data Index: 1712127 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9426. Min Act: -0.1700
Data Index: 4165402 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9739. Min Act: -0.1700
Data Index: 1760676 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9426. Min Act: -0.1700
Data Index: 5599084 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9114. Min Act: -0.1700
Data Index: 4759423 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.9114. Min Act: -0.1700
Data Index: 4883266 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 3616310 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 6110196 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 6648245 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 7160737 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 8182809 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 3707428 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 3385851 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0989. Min Range: -5.0989
Max Act: 4.8801. Min Act: -0.1700
Data Index: 2497249 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19