Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1124 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.5212. Min Act: -0.1700
Data Index: 889790 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.3650. Min Act: -0.1700
Data Index: 8768681 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.3025. Min Act: -0.1700
Data Index: 1000128 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.3025. Min Act: -0.1700
Data Index: 6445785 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.2400. Min Act: -0.1700
Data Index: 6433362 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.2400. Min Act: -0.1700
Data Index: 1785700 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.1462. Min Act: -0.1700
Data Index: 2604525 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.1462. Min Act: -0.1700
Data Index: 8150512 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.1462. Min Act: -0.1700
Data Index: 4498908 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.1149. Min Act: -0.1700
Data Index: 5554409 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.1462. Min Act: -0.1700
Data Index: 241659 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0837. Min Act: -0.1700
Data Index: 5173171 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0837. Min Act: -0.1700
Data Index: 2896278 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0524. Min Act: -0.1700
Data Index: 8375445 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0524. Min Act: -0.1700
Data Index: 3231021 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0524. Min Act: -0.1700
Data Index: 4063938 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0524. Min Act: -0.1700
Data Index: 8638263 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5212. Min Range: -4.5212
Max Act: 3.9899. Min Act: -0.1700
Data Index: 6045489 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0212. Min Act: -0.1700
Data Index: 3400355 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5212. Min Range: -4.5212
Max Act: 4.0524. Min Act: -0.1700
Data Index: 3005286 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19