Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3661406 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3661389 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.1917. Min Act: -0.1700
Data Index: 8387447 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.0979. Min Act: -0.1700
Data Index: 4200615 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.0979. Min Act: -0.1700
Data Index: 3344430 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.0667. Min Act: -0.1700
Data Index: 2361246 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3167. Min Range: -5.3167
Max Act: 5.0354. Min Act: -0.1700
Data Index: 8173644 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9729. Min Act: -0.1700
Data Index: 920892 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9729. Min Act: -0.1700
Data Index: 5067928 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9729. Min Act: -0.1700
Data Index: 606810 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 6612106 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 8217528 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 8173639 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 7678802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 156643 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9417. Min Act: -0.1700
Data Index: 915665 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9104. Min Act: -0.1700
Data Index: 3805771 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2029400 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.8792. Min Act: -0.1700
Data Index: 920633 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3167. Min Range: -5.3167
Max Act: 4.9104. Min Act: -0.1700
Data Index: 6668650 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19