Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.8816. Min Act: -0.1700
Data Index: 707450 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6941. Min Act: -0.1700
Data Index: 7469563 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6941. Min Act: -0.1700
Data Index: 4411276 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6316. Min Act: -0.1700
Data Index: 7549459 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6316. Min Act: -0.1700
Data Index: 5499301 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6004. Min Act: -0.1700
Data Index: 7336911 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.6004. Min Act: -0.1700
Data Index: 2382451 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5379. Min Act: -0.1700
Data Index: 3609379 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5379. Min Act: -0.1700
Data Index: 678973 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5379. Min Act: -0.1700
Data Index: 1821928 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5379. Min Act: -0.1700
Data Index: 3541189 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5066. Min Act: -0.1700
Data Index: 430641 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5066. Min Act: -0.1700
Data Index: 4537753 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4754. Min Act: -0.1700
Data Index: 1715830 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.5066. Min Act: -0.1700
Data Index: 8367307 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4754. Min Act: -0.1700
Data Index: 2828977 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4441. Min Act: -0.1700
Data Index: 8425533 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4441. Min Act: -0.1700
Data Index: 2170945 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4129. Min Act: -0.1700
Data Index: 3120821 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8816. Min Range: -4.8816
Max Act: 4.4129. Min Act: -0.1700
Data Index: 39863 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19