Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.6608. Min Act: -0.1700
Data Index: 7662077 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5982. Min Act: -0.1700
Data Index: 3697184 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4886. Min Act: -0.1700
Data Index: 843845 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5042. Min Act: -0.1700
Data Index: 4491476 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5042. Min Act: -0.1700
Data Index: 7975241 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4572. Min Act: -0.1700
Data Index: 934780 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4572. Min Act: -0.1700
Data Index: 4578494 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4572. Min Act: -0.1700
Data Index: 1941194 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4572. Min Act: -0.1700
Data Index: 3884879 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4572. Min Act: -0.1700
Data Index: 3081562 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4416. Min Act: -0.1700
Data Index: 621268 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4416. Min Act: -0.1700
Data Index: 3670309 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 5580269 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 1773252 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 4316670 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3945. Min Act: -0.1700
Data Index: 4233399 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 3041564 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 6212037 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3945. Min Act: -0.1700
Data Index: 1860977 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3945. Min Act: -0.1700
Data Index: 4474754 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19