Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.7129. Min Act: -0.1700
Data Index: 4501244 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.6817. Min Act: -0.1700
Data Index: 2178671 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.6192. Min Act: -0.1700
Data Index: 3806820 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.6192. Min Act: -0.1700
Data Index: 5468964 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.5879. Min Act: -0.1700
Data Index: 798921 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.5254. Min Act: -0.1700
Data Index: 3153797 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.5254. Min Act: -0.1700
Data Index: 7170693 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4942. Min Act: -0.1700
Data Index: 3041150 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4942. Min Act: -0.1700
Data Index: 3079456 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4629. Min Act: -0.1700
Data Index: 1189619 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4942. Min Act: -0.1700
Data Index: 1080901 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4942. Min Act: -0.1700
Data Index: 5836542 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4317. Min Act: -0.1700
Data Index: 3051656 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4004. Min Act: -0.1700
Data Index: 5880906 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.4004. Min Act: -0.1700
Data Index: 7487312 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.3692. Min Act: -0.1700
Data Index: 1276690 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.3692. Min Act: -0.1700
Data Index: 15364 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.3692. Min Act: -0.1700
Data Index: 5620473 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.3379. Min Act: -0.1700
Data Index: 4108609 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7129. Min Range: -6.7129
Max Act: 6.3379. Min Act: -0.1700
Data Index: 7362230 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19