Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.0619. Min Range: -5.0619
Max Act: 5.0619. Min Act: -0.1700
Data Index: 6892602 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0619. Min Range: -5.0619
Max Act: 5.0619. Min Act: -0.1700
Data Index: 2654657 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9994. Min Act: -0.1700
Data Index: 8094576 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9994. Min Act: -0.1700
Data Index: 3277013 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9681. Min Act: -0.1700
Data Index: 4376639 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1150429 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9369. Min Act: -0.1700
Data Index: 7549327 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9056. Min Act: -0.1700
Data Index: 2967624 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.9056. Min Act: -0.1700
Data Index: 6354533 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8744. Min Act: -0.1700
Data Index: 7285704 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8744. Min Act: -0.1700
Data Index: 7411140 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8744. Min Act: -0.1700
Data Index: 7024061 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8431. Min Act: -0.1700
Data Index: 5128498 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8431. Min Act: -0.1700
Data Index: 7753216 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8431. Min Act: -0.1700
Data Index: 8033073 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.8431. Min Act: -0.1700
Data Index: 6327781 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.7494. Min Act: -0.1700
Data Index: 1806683 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.7806. Min Act: -0.1700
Data Index: 6055294 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.7806. Min Act: -0.1700
Data Index: 1910059 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0619. Min Range: -5.0619
Max Act: 4.7494. Min Act: -0.1700
Data Index: 1824099 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19