Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5488 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.1086. Min Act: -0.1700
Data Index: 4509872 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.0461. Min Act: -0.1700
Data Index: 5688996 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.0148. Min Act: -0.1700
Data Index: 7309644 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.0148. Min Act: -0.1700
Data Index: 1537723 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.0148. Min Act: -0.1700
Data Index: 6671729 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1086. Min Range: -6.1086
Max Act: 6.0148. Min Act: -0.1700
Data Index: 8824335 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.9523. Min Act: -0.1700
Data Index: 7450703 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8898. Min Act: -0.1700
Data Index: 8708938 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8586. Min Act: -0.1700
Data Index: 5583968 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8586. Min Act: -0.1700
Data Index: 1056780 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7961. Min Act: -0.1700
Data Index: 6364703 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8273. Min Act: -0.1700
Data Index: 4029996 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.8273. Min Act: -0.1700
Data Index: 2485962 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7961. Min Act: -0.1700
Data Index: 51338 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7648. Min Act: -0.1700
Data Index: 5009994 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7961. Min Act: -0.1700
Data Index: 6778155 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7648. Min Act: -0.1700
Data Index: 5866823 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7648. Min Act: -0.1700
Data Index: 2457480 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7648. Min Act: -0.1700
Data Index: 173662 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1086. Min Range: -6.1086
Max Act: 5.7336. Min Act: -0.1700
Data Index: 4736591 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19