Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2325 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.6786. Min Act: -0.1700
Data Index: 8636327 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.6161. Min Act: -0.1700
Data Index: 3747994 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.6161. Min Act: -0.1700
Data Index: 6260998 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5848. Min Act: -0.1700
Data Index: 7248215 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.6161. Min Act: -0.1700
Data Index: 3168098 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5848. Min Act: -0.1700
Data Index: 3774062 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5848. Min Act: -0.1700
Data Index: 372146 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 3867763 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5848. Min Act: -0.1700
Data Index: 8818916 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 6233937 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 220490 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5903671 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 7439744 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5848. Min Act: -0.1700
Data Index: 994567 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5223. Min Act: -0.1700
Data Index: 4556540 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5223. Min Act: -0.1700
Data Index: 407710 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5223. Min Act: -0.1700
Data Index: 6225282 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.4910. Min Act: -0.1700
Data Index: 8278360 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5535. Min Act: -0.1700
Data Index: 8678187 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6786. Min Range: -4.6786
Max Act: 4.5223. Min Act: -0.1700
Data Index: 1765357 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19