Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2027 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4229. Min Range: -6.4229
Max Act: 6.4229. Min Act: -0.1700
Data Index: 4815403 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4229. Min Range: -6.4229
Max Act: 6.1729. Min Act: -0.1700
Data Index: 547756 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4229. Min Range: -6.4229
Max Act: 6.1104. Min Act: -0.1700
Data Index: 4113631 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4229. Min Range: -6.4229
Max Act: 6.0479. Min Act: -0.1700
Data Index: 6167741 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 162969 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9854. Min Act: -0.1700
Data Index: 3401736 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4556192 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9854. Min Act: -0.1700
Data Index: 7912151 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 6177597 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 8027027 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9229. Min Act: -0.1700
Data Index: 856203 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9229. Min Act: -0.1700
Data Index: 420907 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9854. Min Act: -0.1700
Data Index: 4865125 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 3093699 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9542. Min Act: -0.1700
Data Index: 1285039 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.8917. Min Act: -0.1700
Data Index: 5135433 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.8917. Min Act: -0.1700
Data Index: 348 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.8917. Min Act: -0.1700
Data Index: 949343 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.8917. Min Act: -0.1700
Data Index: 8482388 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4229. Min Range: -6.4229
Max Act: 5.9229. Min Act: -0.1700
Data Index: 7793692 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19