Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.4151. Min Act: -0.1700
Data Index: 2335645 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.4151. Min Act: -0.1700
Data Index: 8250237 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.3214. Min Act: -0.1700
Data Index: 1348069 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4097325 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.2589. Min Act: -0.1700
Data Index: 1624815 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1964. Min Act: -0.1700
Data Index: 8518476 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1651. Min Act: -0.1700
Data Index: 7410394 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1339. Min Act: -0.1700
Data Index: 217509 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1339. Min Act: -0.1700
Data Index: 4878178 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1026. Min Act: -0.1700
Data Index: 5838980 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1339. Min Act: -0.1700
Data Index: 2955737 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1026. Min Act: -0.1700
Data Index: 1169264 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.1026. Min Act: -0.1700
Data Index: 8678638 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0714. Min Act: -0.1700
Data Index: 3571916 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0714. Min Act: -0.1700
Data Index: 5339985 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0401. Min Act: -0.1700
Data Index: 7586276 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0401. Min Act: -0.1700
Data Index: 4521159 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0088. Min Act: -0.1700
Data Index: 3502892 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0088. Min Act: -0.1700
Data Index: 4741430 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4151. Min Range: -4.4151
Max Act: 4.0401. Min Act: -0.1700
Data Index: 6643069 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19