Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4325 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.6761. Min Act: -0.1700
Data Index: 3179365 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.4261. Min Act: -0.1700
Data Index: 8482823 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.1761. Min Act: -0.1700
Data Index: 6872503 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.1761. Min Act: -0.1700
Data Index: 7819355 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.1136. Min Act: -0.1700
Data Index: 6500858 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.0511. Min Act: -0.1700
Data Index: 4625301 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6761. Min Range: -8.6761
Max Act: 8.0511. Min Act: -0.1700
Data Index: 5482264 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9886. Min Act: -0.1700
Data Index: 7945775 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9886. Min Act: -0.1700
Data Index: 1325995 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9886. Min Act: -0.1700
Data Index: 5793438 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9886. Min Act: -0.1700
Data Index: 8004677 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9261. Min Act: -0.1700
Data Index: 3307303 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9886. Min Act: -0.1700
Data Index: 1631622 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9261. Min Act: -0.1700
Data Index: 4484980 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.9261. Min Act: -0.1700
Data Index: 3070998 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.8948. Min Act: -0.1700
Data Index: 5699118 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.8948. Min Act: -0.1700
Data Index: 65418 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.8948. Min Act: -0.1700
Data Index: 3762859 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.8636. Min Act: -0.1700
Data Index: 3466398 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6761. Min Range: -8.6761
Max Act: 7.8636. Min Act: -0.1700
Data Index: 8506774 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19