Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 658 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.9931. Min Act: -0.1700
Data Index: 3239343 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 5378948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1535980 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6494. Min Act: -0.1700
Data Index: 4369071 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1516319 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5869. Min Act: -0.1700
Data Index: 7638221 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5556. Min Act: -0.1700
Data Index: 4721153 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5556. Min Act: -0.1700
Data Index: 6316115 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5556. Min Act: -0.1700
Data Index: 1665022 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5556. Min Act: -0.1700
Data Index: 8615226 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5244. Min Act: -0.1700
Data Index: 3867731 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5244. Min Act: -0.1700
Data Index: 7667884 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.5244. Min Act: -0.1699
Data Index: 483446 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4931. Min Act: -0.1700
Data Index: 2746273 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4931. Min Act: -0.1700
Data Index: 5795900 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4619. Min Act: -0.1700
Data Index: 459977 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4619. Min Act: -0.1700
Data Index: 6989336 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4619. Min Act: -0.1700
Data Index: 1946230 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.3994. Min Act: -0.1700
Data Index: 95074 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9931. Min Range: -5.9931
Max Act: 5.4306. Min Act: -0.1700
Data Index: 4885563 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19