Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 181 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.7276. Min Act: -0.1700
Data Index: 1503626 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.6651. Min Act: -0.1700
Data Index: 7514931 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.6026. Min Act: -0.1700
Data Index: 1503639 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.4776. Min Act: -0.1700
Data Index: 1503636 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.4776. Min Act: -0.1700
Data Index: 8295339 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.4151. Min Act: -0.1700
Data Index: 346159 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.3526. Min Act: -0.1700
Data Index: 7879483 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.3526. Min Act: -0.1700
Data Index: 4477600 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.3214. Min Act: -0.1700
Data Index: 5740692 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2901. Min Act: -0.1700
Data Index: 7269033 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2901. Min Act: -0.1700
Data Index: 346165 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2589. Min Act: -0.1700
Data Index: 7879484 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2589. Min Act: -0.1700
Data Index: 595317 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2276. Min Act: -0.1700
Data Index: 7879493 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2276. Min Act: -0.1700
Data Index: 8295343 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.1964. Min Act: -0.1700
Data Index: 4920006 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.2589. Min Act: -0.1700
Data Index: 346177 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.1964. Min Act: -0.1700
Data Index: 1503646 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.1964. Min Act: -0.1700
Data Index: 5462240 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7276. Min Range: -8.7276
Max Act: 8.1964. Min Act: -0.1700
Data Index: 5462237 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19