Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2530. Min Range: -7.2530
Max Act: 7.2530. Min Act: -0.1700
Data Index: 4795916 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2530. Min Range: -7.2530
Max Act: 7.1905. Min Act: -0.1700
Data Index: 6425099 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.9092. Min Act: -0.1700
Data Index: 423139 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8780. Min Act: -0.1700
Data Index: 53951 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8467. Min Act: -0.1700
Data Index: 1351886 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8467. Min Act: -0.1700
Data Index: 8815130 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8467. Min Act: -0.1700
Data Index: 6068014 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8467. Min Act: -0.1700
Data Index: 6099354 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8155. Min Act: -0.1700
Data Index: 2007776 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.8155. Min Act: -0.1700
Data Index: 6873458 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7842. Min Act: -0.1700
Data Index: 3089614 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7842. Min Act: -0.1700
Data Index: 6833707 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7842. Min Act: -0.1700
Data Index: 8812285 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7842. Min Act: -0.1700
Data Index: 8377217 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7530. Min Act: -0.1700
Data Index: 3388370 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7530. Min Act: -0.1700
Data Index: 1233037 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7530. Min Act: -0.1700
Data Index: 7941716 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7217. Min Act: -0.1700
Data Index: 6970821 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7217. Min Act: -0.1700
Data Index: 7498567 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2530. Min Range: -7.2530
Max Act: 6.7217. Min Act: -0.1700
Data Index: 195353 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19