Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0367. Min Range: -5.0367
Max Act: 5.0367. Min Act: -0.1700
Data Index: 7090936 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.8180. Min Act: -0.1700
Data Index: 7629618 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.8180. Min Act: -0.1700
Data Index: 471610 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.7242. Min Act: -0.1700
Data Index: 8513853 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5992. Min Act: -0.1700
Data Index: 817483 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.6617. Min Act: -0.1700
Data Index: 3168117 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5680. Min Act: -0.1700
Data Index: 2675258 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5680. Min Act: -0.1700
Data Index: 2180084 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5367. Min Act: -0.1700
Data Index: 6811495 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5367. Min Act: -0.1700
Data Index: 8506501 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5367. Min Act: -0.1700
Data Index: 1575733 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5367. Min Act: -0.1700
Data Index: 78177 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.5055. Min Act: -0.1700
Data Index: 7298796 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4742. Min Act: -0.1700
Data Index: 5626137 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4742. Min Act: -0.1700
Data Index: 4320465 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4742. Min Act: -0.1700
Data Index: 3448050 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4742. Min Act: -0.1700
Data Index: 2227092 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4742. Min Act: -0.1700
Data Index: 6481773 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4117. Min Act: -0.1700
Data Index: 2449000 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0367. Min Range: -5.0367
Max Act: 4.4430. Min Act: -0.1700
Data Index: 7638122 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19