Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 387 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.4916. Min Act: -0.1700
Data Index: 4611850 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.3041. Min Act: -0.1700
Data Index: 2039550 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.3041. Min Act: -0.1700
Data Index: 2039535 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.2416. Min Act: -0.1700
Data Index: 5322128 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1791. Min Act: -0.1700
Data Index: 4926809 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1791. Min Act: -0.1700
Data Index: 2844614 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1791. Min Act: -0.1700
Data Index: 2844628 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1166. Min Act: -0.1700
Data Index: 5322137 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.0541. Min Act: -0.1700
Data Index: 5322156 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1166. Min Act: -0.1700
Data Index: 2264938 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.1791. Min Act: -0.1700
Data Index: 5638210 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.0541. Min Act: -0.1700
Data Index: 1412818 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.0541. Min Act: -0.1700
Data Index: 4159034 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.0541. Min Act: -0.1700
Data Index: 2039547 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4916. Min Range: -8.4916
Max Act: 7.9916. Min Act: -0.1700
Data Index: 3576888 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4916. Min Range: -8.4916
Max Act: 8.0541. Min Act: -0.1700
Data Index: 3676418 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4916. Min Range: -8.4916
Max Act: 7.9916. Min Act: -0.1700
Data Index: 1412833 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4916. Min Range: -8.4916
Max Act: 7.9291. Min Act: -0.1700
Data Index: 6360738 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4916. Min Range: -8.4916
Max Act: 7.9916. Min Act: -0.1700
Data Index: 5657933 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4916. Min Range: -8.4916
Max Act: 7.8666. Min Act: -0.1700
Data Index: 4015114 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19