Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3348. Min Range: -6.3348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 8778513 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3348. Min Range: -6.3348
Max Act: 6.2098. Min Act: -0.1700
Data Index: 3565983 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3348. Min Range: -6.3348
Max Act: 6.1160. Min Act: -0.1700
Data Index: 4299945 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3348. Min Range: -6.3348
Max Act: 6.0535. Min Act: -0.1700
Data Index: 1116754 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9910. Min Act: -0.1700
Data Index: 1553888 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9598. Min Act: -0.1700
Data Index: 3881034 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9285. Min Act: -0.1700
Data Index: 7728448 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9285. Min Act: -0.1700
Data Index: 1286854 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9285. Min Act: -0.1700
Data Index: 176246 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.9285. Min Act: -0.1700
Data Index: 4222717 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8660. Min Act: -0.1700
Data Index: 352026 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8973. Min Act: -0.1700
Data Index: 7956430 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8973. Min Act: -0.1700
Data Index: 3066729 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8660. Min Act: -0.1700
Data Index: 1904187 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8973. Min Act: -0.1700
Data Index: 352025 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8660. Min Act: -0.1700
Data Index: 8766639 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8660. Min Act: -0.1700
Data Index: 120795 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8660. Min Act: -0.1700
Data Index: 5764865 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8348. Min Act: -0.1700
Data Index: 8766640 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3348. Min Range: -6.3348
Max Act: 5.8348. Min Act: -0.1700
Data Index: 3841552 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19