Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 3893983 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.9547. Min Act: -0.1700
Data Index: 3175246 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 6954459 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 8718528 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.8922. Min Act: -0.1700
Data Index: 2644987 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.5172. Min Act: -0.1700
Data Index: 7136173 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.5172. Min Act: -0.1700
Data Index: 4377218 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3922. Min Act: -0.1700
Data Index: 2928004 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3922. Min Act: -0.1700
Data Index: 7641777 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3922. Min Act: -0.1700
Data Index: 6042518 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3922. Min Act: -0.1700
Data Index: 2358152 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3922. Min Act: -0.1700
Data Index: 4170675 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.3297. Min Act: -0.1700
Data Index: 4150052 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2672. Min Act: -0.1700
Data Index: 5249215 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2672. Min Act: -0.1700
Data Index: 670131 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2672. Min Act: -0.1700
Data Index: 2448327 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2672. Min Act: -0.1700
Data Index: 239752 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2047. Min Act: -0.1700
Data Index: 6872656 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2047. Min Act: -0.1700
Data Index: 1772447 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9547. Min Range: -8.9547
Max Act: 8.2047. Min Act: -0.1700
Data Index: 2607233 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19