Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.7785. Min Act: -0.1700
Data Index: 4047326 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.7473. Min Act: -0.1700
Data Index: 3989572 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.7473. Min Act: -0.1700
Data Index: 7819200 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.7160. Min Act: -0.1700
Data Index: 381342 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.7160. Min Act: -0.1700
Data Index: 2246307 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6534. Min Act: -0.1700
Data Index: 3513251 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6847. Min Act: -0.1700
Data Index: 1394471 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6534. Min Act: -0.1700
Data Index: 3541985 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6534. Min Act: -0.1700
Data Index: 2878907 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6221. Min Act: -0.1700
Data Index: 6910154 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6221. Min Act: -0.1700
Data Index: 3840266 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6534. Min Act: -0.1700
Data Index: 6909154 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6221. Min Act: -0.1700
Data Index: 7765625 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6221. Min Act: -0.1700
Data Index: 7850820 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.6221. Min Act: -0.1700
Data Index: 1541790 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.5908. Min Act: -0.1700
Data Index: 771763 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.5908. Min Act: -0.1700
Data Index: 2664237 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.5595. Min Act: -0.1700
Data Index: 8448113 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.5908. Min Act: -0.1700
Data Index: 3884108 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7785. Min Range: -3.7785
Max Act: 3.5908. Min Act: -0.1700
Data Index: 483255 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19