Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1189. Min Range: -10.1189
Max Act: 10.1189. Min Act: -0.1700
Data Index: 311069 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.7439. Min Act: -0.1700
Data Index: 5767607 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.6189. Min Act: -0.1700
Data Index: 3391965 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.6814. Min Act: -0.1700
Data Index: 1671956 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.6189. Min Act: -0.1700
Data Index: 3268965 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3689. Min Act: -0.1700
Data Index: 6470301 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3689. Min Act: -0.1700
Data Index: 5649732 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3689. Min Act: -0.1700
Data Index: 4827622 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3689. Min Act: -0.1700
Data Index: 6727950 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3064. Min Act: -0.1700
Data Index: 1336825 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3064. Min Act: -0.1700
Data Index: 6304719 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3064. Min Act: -0.1700
Data Index: 5767606 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.3064. Min Act: -0.1700
Data Index: 3965985 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.2439. Min Act: -0.1700
Data Index: 3835965 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.2439. Min Act: -0.1700
Data Index: 3858867 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.1189. Min Act: -0.1700
Data Index: 4040177 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.1189. Min Act: -0.1700
Data Index: 411865 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.1189. Min Act: -0.1700
Data Index: 2123165 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.1189. Min Act: -0.1700
Data Index: 530670 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1189. Min Range: -10.1189
Max Act: 9.0564. Min Act: -0.1700
Data Index: 803169 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19