Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6383 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1179. Min Range: -9.1179
Max Act: 9.1179. Min Act: -0.1700
Data Index: 3467899 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1179. Min Range: -9.1179
Max Act: 9.0554. Min Act: -0.1700
Data Index: 2576086 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1179. Min Range: -9.1179
Max Act: 9.0554. Min Act: -0.1700
Data Index: 1145887 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.9929. Min Act: -0.1700
Data Index: 8321637 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.9304. Min Act: -0.1700
Data Index: 7719495 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.9304. Min Act: -0.1700
Data Index: 80668 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 3491039 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 2007990 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 3085758 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 3395126 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.9304. Min Act: -0.1700
Data Index: 7727209 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 3668913 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8679. Min Act: -0.1700
Data Index: 6180081 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8054. Min Act: -0.1700
Data Index: 8512194 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8054. Min Act: -0.1700
Data Index: 7144049 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8054. Min Act: -0.1700
Data Index: 8513010 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8054. Min Act: -0.1700
Data Index: 8826390 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.8054. Min Act: -0.1700
Data Index: 1726087 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.7429. Min Act: -0.1700
Data Index: 666487 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1179. Min Range: -9.1179
Max Act: 8.7429. Min Act: -0.1700
Data Index: 7204843 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19