Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.6816. Min Act: -0.1700
Data Index: 7072981 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.6191. Min Act: -0.1700
Data Index: 2170638 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.4941. Min Act: -0.1700
Data Index: 1670823 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.3378. Min Act: -0.1700
Data Index: 468080 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.2753. Min Act: -0.1700
Data Index: 106899 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.2441. Min Act: -0.1700
Data Index: 3924291 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.1816. Min Act: -0.1700
Data Index: 5162269 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.1191. Min Act: -0.1700
Data Index: 4658133 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.0566. Min Act: -0.1700
Data Index: 3356155 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.0566. Min Act: -0.1700
Data Index: 8551034 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.0253. Min Act: -0.1700
Data Index: 6866378 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6816. Min Range: -7.6816
Max Act: 7.0253. Min Act: -0.1700
Data Index: 945190 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9941. Min Act: -0.1700
Data Index: 6004220 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9628. Min Act: -0.1700
Data Index: 4888141 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9628. Min Act: -0.1700
Data Index: 7617510 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9628. Min Act: -0.1700
Data Index: 3333816 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9628. Min Act: -0.1700
Data Index: 1215020 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9316. Min Act: -0.1700
Data Index: 4184525 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9316. Min Act: -0.1700
Data Index: 3846943 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6816. Min Range: -7.6816
Max Act: 6.9003. Min Act: -0.1700
Data Index: 1808720 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19