Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.2399. Min Act: -0.1700
Data Index: 1441122 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 6719799 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 2166193 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 4837554 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1774. Min Act: -0.1700
Data Index: 2466469 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 7075230 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1461. Min Act: -0.1700
Data Index: 31033 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 6413332 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.1149. Min Act: -0.1700
Data Index: 5214521 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.0836. Min Act: -0.1700
Data Index: 6030717 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.0524. Min Act: -0.1700
Data Index: 5090749 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.0524. Min Act: -0.1700
Data Index: 3061584 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.0211. Min Act: -0.1700
Data Index: 1701493 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2399. Min Range: -5.2399
Max Act: 5.0211. Min Act: -0.1700
Data Index: 4798778 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9899. Min Act: -0.1700
Data Index: 6548309 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5188762 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9899. Min Act: -0.1700
Data Index: 1250137 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4511537 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4712188 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2399. Min Range: -5.2399
Max Act: 4.9586. Min Act: -0.1700
Data Index: 31032 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19