Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.3146. Min Act: -0.1700
Data Index: 6005770 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2832. Min Act: -0.1700
Data Index: 262475 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2518. Min Act: -0.1700
Data Index: 3775637 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2361. Min Act: -0.1700
Data Index: 5432381 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2361. Min Act: -0.1700
Data Index: 4611947 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2361. Min Act: -0.1700
Data Index: 7268729 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2361. Min Act: -0.1700
Data Index: 1741722 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2046. Min Act: -0.1700
Data Index: 2584078 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.2046. Min Act: -0.1700
Data Index: 6404050 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1732. Min Act: -0.1700
Data Index: 3863834 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1574. Min Act: -0.1700
Data Index: 6681054 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1574. Min Act: -0.1700
Data Index: 6627786 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1574. Min Act: -0.1700
Data Index: 3923290 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1260. Min Act: -0.1700
Data Index: 2476822 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1260. Min Act: -0.1700
Data Index: 6848396 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1417. Min Act: -0.1700
Data Index: 210823 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.0944. Min Act: -0.1700
Data Index: 1459320 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.0944. Min Act: -0.1700
Data Index: 2655689 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1417. Min Act: -0.1700
Data Index: 1675445 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3146. Min Range: -3.3146
Max Act: 3.1417. Min Act: -0.1700
Data Index: 1988090 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19