Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 651 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1365. Min Range: -8.1365
Max Act: 8.1365. Min Act: -0.1700
Data Index: 5052607 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1365. Min Range: -8.1365
Max Act: 8.0115. Min Act: -0.1700
Data Index: 8021273 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.8865. Min Act: -0.1700
Data Index: 7768231 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.6990. Min Act: -0.1700
Data Index: 1098427 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.5740. Min Act: -0.1700
Data Index: 609215 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.5427. Min Act: -0.1700
Data Index: 1351051 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.5427. Min Act: -0.1700
Data Index: 6773751 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.5115. Min Act: -0.1700
Data Index: 8192801 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.5115. Min Act: -0.1700
Data Index: 3271052 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.4490. Min Act: -0.1700
Data Index: 3547180 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 6579565 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 4857568 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.4177. Min Act: -0.1700
Data Index: 3665433 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.4177. Min Act: -0.1700
Data Index: 7091684 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 5867224 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 2350971 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 1563168 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3865. Min Act: -0.1700
Data Index: 6506228 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3552. Min Act: -0.1700
Data Index: 7095303 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1365. Min Range: -8.1365
Max Act: 7.3552. Min Act: -0.1700
Data Index: 3896137 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19