Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.4088. Min Act: -0.1700
Data Index: 170563 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.3775. Min Act: -0.1700
Data Index: 962229 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.2213. Min Act: -0.1700
Data Index: 5635762 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 5283704 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 7861542 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 1376854 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 296023 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0963. Min Act: -0.1700
Data Index: 2097685 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 8104249 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.1275. Min Act: -0.1700
Data Index: 2441330 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0963. Min Act: -0.1700
Data Index: 7563516 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 7933967 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 4950971 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 8397409 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0650. Min Act: -0.1700
Data Index: 4358225 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4758823 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 8637480 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 6276290 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4088. Min Range: -6.4088
Max Act: 6.0338. Min Act: -0.1700
Data Index: 5531481 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4088. Min Range: -6.4088
Max Act: 5.9400. Min Act: -0.1700
Data Index: 6607831 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19