Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3727 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.9745. Min Act: -0.1700
Data Index: 6005741 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.9432. Min Act: -0.1700
Data Index: 2321614 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.9119. Min Act: -0.1700
Data Index: 303793 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.9119. Min Act: -0.1700
Data Index: 8016424 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.9119. Min Act: -0.1700
Data Index: 6005740 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8807. Min Act: -0.1700
Data Index: 7195864 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8807. Min Act: -0.1700
Data Index: 7745146 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 7477123 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8807. Min Act: -0.1700
Data Index: 1251492 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 5102680 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 7443165 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 4175700 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 5559833 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 8572613 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8494. Min Act: -0.1700
Data Index: 4745250 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8181. Min Act: -0.1700
Data Index: 5102681 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8181. Min Act: -0.1700
Data Index: 6407914 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8181. Min Act: -0.1700
Data Index: 7512419 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8181. Min Act: -0.1700
Data Index: 4225414 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9745. Min Range: -3.9745
Max Act: 3.8181. Min Act: -0.1700
Data Index: 7910553 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19