Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.9796. Min Act: -0.1700
Data Index: 2429534 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.9484. Min Act: -0.1700
Data Index: 274087 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.8546. Min Act: -0.1700
Data Index: 1526170 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7921. Min Act: -0.1700
Data Index: 3707081 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7296. Min Act: -0.1700
Data Index: 2392059 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7609. Min Act: -0.1700
Data Index: 474657 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7609. Min Act: -0.1700
Data Index: 3640911 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7296. Min Act: -0.1700
Data Index: 1956507 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7296. Min Act: -0.1700
Data Index: 5325260 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7296. Min Act: -0.1700
Data Index: 6506863 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.7296. Min Act: -0.1700
Data Index: 7300414 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6984. Min Act: -0.1700
Data Index: 6682505 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6671. Min Act: -0.1700
Data Index: 134773 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6671. Min Act: -0.1700
Data Index: 5975993 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6671. Min Act: -0.1700
Data Index: 6578657 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6359. Min Act: -0.1700
Data Index: 6460369 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6359. Min Act: -0.1700
Data Index: 7237794 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6359. Min Act: -0.1700
Data Index: 6607929 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6046. Min Act: -0.1700
Data Index: 4897023 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9796. Min Range: -4.9796
Max Act: 4.6046. Min Act: -0.1700
Data Index: 6781218 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19