Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.1162. Min Act: -0.1700
Data Index: 4772084 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0827. Min Act: -0.1700
Data Index: 3684839 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0660. Min Act: -0.1700
Data Index: 2160770 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0660. Min Act: -0.1700
Data Index: 6516053 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0660. Min Act: -0.1700
Data Index: 8577051 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0492. Min Act: -0.1700
Data Index: 2268848 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0660. Min Act: -0.1700
Data Index: 3590177 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0323. Min Act: -0.1700
Data Index: 2478286 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0492. Min Act: -0.1700
Data Index: 3942571 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0323. Min Act: -0.1700
Data Index: 4316953 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0155. Min Act: -0.1700
Data Index: 343767 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0155. Min Act: -0.1700
Data Index: 7272928 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0155. Min Act: -0.1700
Data Index: 2058027 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1162. Min Range: -2.1162
Max Act: 2.0155. Min Act: -0.1700
Data Index: 2806459 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9816. Min Act: -0.1700
Data Index: 8178750 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9986. Min Act: -0.1700
Data Index: 2816128 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9647. Min Act: -0.1700
Data Index: 7587827 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9647. Min Act: -0.1700
Data Index: 5257147 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9647. Min Act: -0.1700
Data Index: 8766385 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1162. Min Range: -2.1162
Max Act: 1.9647. Min Act: -0.1700
Data Index: 5630196 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19