Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.7983. Min Act: -0.1700
Data Index: 3003789 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.4545. Min Act: -0.1700
Data Index: 3291471 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.4858. Min Act: -0.1700
Data Index: 1831131 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.4858. Min Act: -0.1700
Data Index: 1644400 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.3295. Min Act: -0.1700
Data Index: 4407821 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2670. Min Act: -0.1700
Data Index: 2735047 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2983. Min Act: -0.1700
Data Index: 7778641 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2983. Min Act: -0.1700
Data Index: 7778637 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2670. Min Act: -0.1700
Data Index: 3598987 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2670. Min Act: -0.1700
Data Index: 7968954 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2045. Min Act: -0.1700
Data Index: 3778020 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2045. Min Act: -0.1700
Data Index: 4065213 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2045. Min Act: -0.1700
Data Index: 7865471 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.2045. Min Act: -0.1700
Data Index: 2991407 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 8578885 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 8283267 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1420. Min Act: -0.1700
Data Index: 755287 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.1108. Min Act: -0.1700
Data Index: 6875114 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.0795. Min Act: -0.1700
Data Index: 457351 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7983. Min Range: -6.7983
Max Act: 6.0483. Min Act: -0.1700
Data Index: 3778021 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19