Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1666. Min Range: -7.1666
Max Act: 7.1666. Min Act: -0.1700
Data Index: 5781643 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1666. Min Range: -7.1666
Max Act: 7.1353. Min Act: -0.1700
Data Index: 1339124 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1666. Min Range: -7.1666
Max Act: 7.0103. Min Act: -0.1700
Data Index: 3610021 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.9478. Min Act: -0.1700
Data Index: 1151211 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.9478. Min Act: -0.1700
Data Index: 1604125 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.9478. Min Act: -0.1700
Data Index: 4733647 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.8541. Min Act: -0.1700
Data Index: 859320 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.8228. Min Act: -0.1700
Data Index: 7106399 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.8228. Min Act: -0.1700
Data Index: 3557794 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7916. Min Act: -0.1700
Data Index: 6521618 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7916. Min Act: -0.1700
Data Index: 1810054 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7603. Min Act: -0.1700
Data Index: 5321309 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7916. Min Act: -0.1700
Data Index: 1775996 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7291. Min Act: -0.1700
Data Index: 7522183 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.7603. Min Act: -0.1700
Data Index: 3980323 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3072669 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.6978. Min Act: -0.1700
Data Index: 6246298 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.6978. Min Act: -0.1700
Data Index: 2686839 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3998847 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1666. Min Range: -7.1666
Max Act: 6.6978. Min Act: -0.1700
Data Index: 3097409 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19