Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4815 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4890. Min Range: -7.4890
Max Act: 7.4890. Min Act: -0.1700
Data Index: 8362805 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4890. Min Range: -7.4890
Max Act: 7.3015. Min Act: -0.1700
Data Index: 135552 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4890. Min Range: -7.4890
Max Act: 7.2702. Min Act: -0.1700
Data Index: 3652634 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4890. Min Range: -7.4890
Max Act: 7.1140. Min Act: -0.1700
Data Index: 1970335 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4890. Min Range: -7.4890
Max Act: 7.0202. Min Act: -0.1700
Data Index: 1692112 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9890. Min Act: -0.1700
Data Index: 1616318 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4954149 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9577. Min Act: -0.1700
Data Index: 6696698 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9265. Min Act: -0.1700
Data Index: 8043287 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9265. Min Act: -0.1700
Data Index: 2997195 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6525700 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.9577. Min Act: -0.1700
Data Index: 2119984 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8640. Min Act: -0.1700
Data Index: 5810971 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6963929 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8952. Min Act: -0.1700
Data Index: 7198477 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8640. Min Act: -0.1700
Data Index: 5697835 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.7702. Min Act: -0.1700
Data Index: 673465 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8015. Min Act: -0.1700
Data Index: 2478134 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8015. Min Act: -0.1700
Data Index: 6705105 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4890. Min Range: -7.4890
Max Act: 6.8015. Min Act: -0.1700
Data Index: 1880717 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19