Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2739 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1120. Min Range: -6.1120
Max Act: 6.1120. Min Act: -0.1700
Data Index: 1344614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.9870. Min Act: -0.1700
Data Index: 5031560 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.9557. Min Act: -0.1700
Data Index: 6795054 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.9245. Min Act: -0.1700
Data Index: 2756744 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.9245. Min Act: -0.1700
Data Index: 4131848 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8932. Min Act: -0.1700
Data Index: 2219105 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8932. Min Act: -0.1700
Data Index: 473259 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8620. Min Act: -0.1700
Data Index: 3735014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8620. Min Act: -0.1700
Data Index: 2303663 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8932. Min Act: -0.1700
Data Index: 75616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8620. Min Act: -0.1700
Data Index: 8512960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8620. Min Act: -0.1700
Data Index: 2674682 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8620. Min Act: -0.1700
Data Index: 309126 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 2444108 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 3265985 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 7659068 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1699
Data Index: 1416769 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 8293831 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 573076 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1120. Min Range: -6.1120
Max Act: 5.8307. Min Act: -0.1700
Data Index: 2718998 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19