Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.4134. Min Act: -0.1700
Data Index: 4493927 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.4134. Min Act: -0.1700
Data Index: 3524630 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3822. Min Act: -0.1700
Data Index: 4767948 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3509. Min Act: -0.1700
Data Index: 1884557 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3509. Min Act: -0.1700
Data Index: 3874303 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3197. Min Act: -0.1700
Data Index: 7921560 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3197. Min Act: -0.1700
Data Index: 5495479 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3197. Min Act: -0.1700
Data Index: 7038117 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.3509. Min Act: -0.1700
Data Index: 3018782 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2884. Min Act: -0.1700
Data Index: 4737812 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2884. Min Act: -0.1700
Data Index: 2551855 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2884. Min Act: -0.1700
Data Index: 4430443 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2884. Min Act: -0.1700
Data Index: 6955797 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2884. Min Act: -0.1700
Data Index: 4161175 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2571. Min Act: -0.1700
Data Index: 2551857 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2571. Min Act: -0.1700
Data Index: 6468632 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2259. Min Act: -0.1700
Data Index: 7036841 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2571. Min Act: -0.1700
Data Index: 6843612 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.1946. Min Act: -0.1700
Data Index: 7561780 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4134. Min Range: -4.4134
Max Act: 4.2259. Min Act: -0.1700
Data Index: 1946485 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19