Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1160. Min Range: -8.1160
Max Act: 8.1160. Min Act: -0.1700
Data Index: 8564563 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.8660. Min Act: -0.1700
Data Index: 2099225 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.8347. Min Act: -0.1700
Data Index: 2218294 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.7722. Min Act: -0.1700
Data Index: 5728681 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.7722. Min Act: -0.1700
Data Index: 4796181 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.6160. Min Act: -0.1700
Data Index: 5582724 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5535. Min Act: -0.1700
Data Index: 6226933 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5535. Min Act: -0.1700
Data Index: 5527325 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5222. Min Act: -0.1700
Data Index: 7480124 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5535. Min Act: -0.1700
Data Index: 4854181 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3231910 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.5222. Min Act: -0.1700
Data Index: 3068773 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.4910. Min Act: -0.1700
Data Index: 2297339 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.4597. Min Act: -0.1700
Data Index: 6383994 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3972. Min Act: -0.1700
Data Index: 3031112 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3972. Min Act: -0.1700
Data Index: 7625554 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3972. Min Act: -0.1700
Data Index: 654384 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3972. Min Act: -0.1700
Data Index: 1935195 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3660. Min Act: -0.1700
Data Index: 1761802 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1160. Min Range: -8.1160
Max Act: 7.3660. Min Act: -0.1700
Data Index: 6971120 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19