Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 813 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.2532. Min Act: -0.1700
Data Index: 1733396 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.2219. Min Act: -0.1700
Data Index: 5080217 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2820771 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2368424 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1907. Min Act: -0.1700
Data Index: 6079686 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1594. Min Act: -0.1700
Data Index: 7791771 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2835353 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1282. Min Act: -0.1700
Data Index: 2057214 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.1282. Min Act: -0.1700
Data Index: 8382771 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0969. Min Act: -0.1700
Data Index: 3674670 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0969. Min Act: -0.1700
Data Index: 3050188 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0969. Min Act: -0.1700
Data Index: 4986252 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0969. Min Act: -0.1700
Data Index: 70713 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0969. Min Act: -0.1700
Data Index: 7560096 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0656. Min Act: -0.1700
Data Index: 7989873 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0656. Min Act: -0.1700
Data Index: 2413759 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0656. Min Act: -0.1700
Data Index: 1031145 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0344. Min Act: -0.1700
Data Index: 6089917 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0656. Min Act: -0.1700
Data Index: 540094 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2532. Min Range: -4.2532
Max Act: 4.0656. Min Act: -0.1700
Data Index: 3070774 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19