Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0183. Min Range: -4.0183
Max Act: 4.0183. Min Act: -0.1700
Data Index: 6937463 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9245. Min Act: -0.1700
Data Index: 4089682 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.8932. Min Act: -0.1700
Data Index: 3917628 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.8620. Min Act: -0.1700
Data Index: 2203890 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7994. Min Act: -0.1700
Data Index: 6758413 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7838. Min Act: -0.1700
Data Index: 4089302 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7838. Min Act: -0.1700
Data Index: 1150563 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7681. Min Act: -0.1700
Data Index: 3621455 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7369. Min Act: -0.1700
Data Index: 4811189 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7369. Min Act: -0.1700
Data Index: 1333411 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7369. Min Act: -0.1700
Data Index: 126591 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7212. Min Act: -0.1700
Data Index: 8485644 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7369. Min Act: -0.1700
Data Index: 3669575 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7056. Min Act: -0.1700
Data Index: 5471857 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7056. Min Act: -0.1700
Data Index: 2922149 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.7056. Min Act: -0.1700
Data Index: 8829438 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.6743. Min Act: -0.1700
Data Index: 4140806 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.6899. Min Act: -0.1700
Data Index: 5198451 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.6899. Min Act: -0.1700
Data Index: 492131 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.6899. Min Act: -0.1700
Data Index: 1950945 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19