Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2254. Min Range: -5.2254
Max Act: 5.2254. Min Act: -0.1700
Data Index: 5658028 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2254. Min Range: -5.2254
Max Act: 5.0379. Min Act: -0.1700
Data Index: 4202110 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2254. Min Range: -5.2254
Max Act: 5.0066. Min Act: -0.1700
Data Index: 3172712 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.9754. Min Act: -0.1700
Data Index: 8732775 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2254. Min Range: -5.2254
Max Act: 5.0066. Min Act: -0.1700
Data Index: 4840584 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.9441. Min Act: -0.1700
Data Index: 8815401 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.9441. Min Act: -0.1700
Data Index: 7495247 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.9129. Min Act: -0.1700
Data Index: 4207415 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.8816. Min Act: -0.1700
Data Index: 1111344 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.8191. Min Act: -0.1700
Data Index: 2011830 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.8191. Min Act: -0.1700
Data Index: 4384541 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.8191. Min Act: -0.1700
Data Index: 840340 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.8191. Min Act: -0.1700
Data Index: 6796944 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7566. Min Act: -0.1700
Data Index: 5599253 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7566. Min Act: -0.1700
Data Index: 3395616 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7879. Min Act: -0.1700
Data Index: 5637673 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7879. Min Act: -0.1700
Data Index: 7029164 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7879. Min Act: -0.1700
Data Index: 8073454 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7879. Min Act: -0.1700
Data Index: 750019 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2254. Min Range: -5.2254
Max Act: 4.7879. Min Act: -0.1700
Data Index: 3796030 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19