Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4996 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.7800. Min Act: -0.1700
Data Index: 4724252 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.6237. Min Act: -0.1700
Data Index: 1131053 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.6237. Min Act: -0.1700
Data Index: 2863970 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.5612. Min Act: -0.1700
Data Index: 2731914 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4987. Min Act: -0.1700
Data Index: 8037095 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4362. Min Act: -0.1700
Data Index: 4581178 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.4050. Min Act: -0.1700
Data Index: 6103294 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3737. Min Act: -0.1700
Data Index: 2370019 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3737. Min Act: -0.1700
Data Index: 8478650 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3425. Min Act: -0.1700
Data Index: 4105269 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3425. Min Act: -0.1700
Data Index: 7879326 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3425. Min Act: -0.1700
Data Index: 1524198 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2455498 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2800. Min Act: -0.1700
Data Index: 950018 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2175. Min Act: -0.1700
Data Index: 4814393 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2487. Min Act: -0.1700
Data Index: 814279 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.2175. Min Act: -0.1700
Data Index: 3528346 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5857560 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.1862. Min Act: -0.1700
Data Index: 8346798 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7800. Min Range: -5.7800
Max Act: 5.1550. Min Act: -0.1700
Data Index: 4009859 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19