Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 826 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4063819 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.4331. Min Act: -0.1700
Data Index: 8110792 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.4331. Min Act: -0.1700
Data Index: 4645607 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.3081. Min Act: -0.1700
Data Index: 8000020 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.2144. Min Act: -0.1700
Data Index: 7893223 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.2769. Min Act: -0.1700
Data Index: 7035051 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.2456. Min Act: -0.1700
Data Index: 178662 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.2144. Min Act: -0.1700
Data Index: 5101521 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.1206. Min Act: -0.1700
Data Index: 59039 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.0894. Min Act: -0.1700
Data Index: 6756632 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.0894. Min Act: -0.1700
Data Index: 5173117 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.0581. Min Act: -0.1700
Data Index: 6529117 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.0581. Min Act: -0.1700
Data Index: 8769510 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9956. Min Act: -0.1700
Data Index: 8515889 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4331. Min Range: -7.4331
Max Act: 7.0269. Min Act: -0.1700
Data Index: 3513343 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9644. Min Act: -0.1700
Data Index: 4901382 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9331. Min Act: -0.1700
Data Index: 345955 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9019. Min Act: -0.1700
Data Index: 201296 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9331. Min Act: -0.1700
Data Index: 4228428 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4331. Min Range: -7.4331
Max Act: 6.9644. Min Act: -0.1700
Data Index: 2847350 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19