Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.7042. Min Act: -0.1700
Data Index: 4465354 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.3604. Min Act: -0.1700
Data Index: 504695 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.2354. Min Act: -0.1700
Data Index: 4869701 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.1104. Min Act: -0.1700
Data Index: 3575528 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0479. Min Act: -0.1700
Data Index: 2977318 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5816308 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0792. Min Act: -0.1700
Data Index: 3191360 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0167. Min Act: -0.1700
Data Index: 4480749 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0479. Min Act: -0.1700
Data Index: 4638191 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0167. Min Act: -0.1700
Data Index: 2928986 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.9854. Min Act: -0.1700
Data Index: 6786033 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.9854. Min Act: -0.1700
Data Index: 4387075 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7042. Min Range: -6.7042
Max Act: 6.0167. Min Act: -0.1700
Data Index: 8396649 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.9542. Min Act: -0.1700
Data Index: 78556 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.9229. Min Act: -0.1700
Data Index: 7671644 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.8604. Min Act: -0.1700
Data Index: 5263133 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.8292. Min Act: -0.1700
Data Index: 3683197 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.7979. Min Act: -0.1700
Data Index: 4480748 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.8292. Min Act: -0.1700
Data Index: 58205 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7042. Min Range: -6.7042
Max Act: 5.7979. Min Act: -0.1700
Data Index: 6853590 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19