Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.7413. Min Act: -0.1700
Data Index: 5662081 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.4596. Min Act: -0.1700
Data Index: 7468810 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.4126. Min Act: -0.1700
Data Index: 4150260 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.4126. Min Act: -0.1700
Data Index: 4091332 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3812. Min Act: -0.1700
Data Index: 4919644 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3655. Min Act: -0.1700
Data Index: 1111465 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3498. Min Act: -0.1700
Data Index: 7698790 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3184. Min Act: -0.1700
Data Index: 833477 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3341. Min Act: -0.1700
Data Index: 5147802 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3027. Min Act: -0.1700
Data Index: 275616 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3341. Min Act: -0.1700
Data Index: 6150439 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3027. Min Act: -0.1700
Data Index: 272009 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2870. Min Act: -0.1700
Data Index: 5450666 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3027. Min Act: -0.1700
Data Index: 7446426 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2870. Min Act: -0.1700
Data Index: 2331672 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2870. Min Act: -0.1700
Data Index: 8589098 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2870. Min Act: -0.1700
Data Index: 7265643 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.3027. Min Act: -0.1700
Data Index: 4327107 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2870. Min Act: -0.1700
Data Index: 4880641 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7413. Min Range: -3.7413
Max Act: 3.2713. Min Act: -0.1700
Data Index: 1634224 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19