Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3711. Min Range: -11.3711
Max Act: 11.3711. Min Act: -0.1700
Data Index: 2502789 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.9336. Min Act: -0.1700
Data Index: 46302 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.8711. Min Act: -0.1700
Data Index: 1199982 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.8711. Min Act: -0.1700
Data Index: 5157713 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.8086. Min Act: -0.1700
Data Index: 2233338 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.7461. Min Act: -0.1700
Data Index: 2641163 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.6836. Min Act: -0.1700
Data Index: 5372194 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.6836. Min Act: -0.1700
Data Index: 7311492 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.5586. Min Act: -0.1700
Data Index: 4282451 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.4961. Min Act: -0.1700
Data Index: 4802844 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.4336. Min Act: -0.1699
Data Index: 1277303 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.3711. Min Act: -0.1700
Data Index: 3202507 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.3711. Min Act: -0.1700
Data Index: 621020 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.3711. Min Act: -0.1700
Data Index: 1217461 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.3711. Min Act: -0.1700
Data Index: 6439286 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.3086. Min Act: -0.1700
Data Index: 7013692 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.2461. Min Act: -0.1700
Data Index: 328120 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.2461. Min Act: -0.1696
Data Index: 7235301 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.2461. Min Act: -0.1700
Data Index: 7377722 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3711. Min Range: -11.3711
Max Act: 10.1211. Min Act: -0.1700
Data Index: 1248254 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19