Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1017 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.5450. Min Act: -0.1700
Data Index: 1740017 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 4599537 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.4825. Min Act: -0.1700
Data Index: 7564691 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.4200. Min Act: -0.1700
Data Index: 6592565 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.4200. Min Act: -0.1700
Data Index: 1417183 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.4200. Min Act: -0.1700
Data Index: 5853005 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3887. Min Act: -0.1700
Data Index: 6947065 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3887. Min Act: -0.1700
Data Index: 7283514 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3887. Min Act: -0.1700
Data Index: 6210250 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3575. Min Act: -0.1700
Data Index: 4089174 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3575. Min Act: -0.1700
Data Index: 4050921 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3575. Min Act: -0.1700
Data Index: 2552823 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3575. Min Act: -0.1700
Data Index: 6163403 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3575. Min Act: -0.1700
Data Index: 85349 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.3262. Min Act: -0.1700
Data Index: 4258466 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.2950. Min Act: -0.1700
Data Index: 3173865 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.2637. Min Act: -0.1700
Data Index: 7452579 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.2950. Min Act: -0.1700
Data Index: 6129095 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.2637. Min Act: -0.1700
Data Index: 943645 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5450. Min Range: -4.5450
Max Act: 4.2950. Min Act: -0.1700
Data Index: 5411665 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19