Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.4730. Min Act: -0.1700
Data Index: 6776812 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.4730. Min Act: -0.1700
Data Index: 7031654 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.3947. Min Act: -0.1700
Data Index: 7339277 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.3633. Min Act: -0.1700
Data Index: 4713984 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.3476. Min Act: -0.1700
Data Index: 5525167 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.3476. Min Act: -0.1700
Data Index: 2729600 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.3005. Min Act: -0.1700
Data Index: 224007 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2848. Min Act: -0.1700
Data Index: 458316 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2534. Min Act: -0.1700
Data Index: 6516259 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2377. Min Act: -0.1700
Data Index: 4766286 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2691. Min Act: -0.1700
Data Index: 7288515 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2220. Min Act: -0.1700
Data Index: 3920660 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2377. Min Act: -0.1700
Data Index: 504464 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2377. Min Act: -0.1700
Data Index: 1734711 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2377. Min Act: -0.1700
Data Index: 6428688 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2220. Min Act: -0.1700
Data Index: 1314447 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2063. Min Act: -0.1700
Data Index: 830782 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2063. Min Act: -0.1700
Data Index: 6502597 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2063. Min Act: -0.1700
Data Index: 1684407 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4730. Min Range: -3.4730
Max Act: 3.2063. Min Act: -0.1700
Data Index: 5558239 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19