Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3856 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.8344. Min Act: -0.1700
Data Index: 5386275 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.6469. Min Act: -0.1700
Data Index: 4011790 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.6469. Min Act: -0.1700
Data Index: 7617043 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.6157. Min Act: -0.1700
Data Index: 6166450 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.5844. Min Act: -0.1700
Data Index: 167107 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.5844. Min Act: -0.1700
Data Index: 62785 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.5219. Min Act: -0.1700
Data Index: 2679577 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.5219. Min Act: -0.1700
Data Index: 1977678 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.5219. Min Act: -0.1700
Data Index: 7854909 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4860322 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4619351 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4907. Min Act: -0.1700
Data Index: 7826590 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4907. Min Act: -0.1700
Data Index: 2010102 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4907. Min Act: -0.1700
Data Index: 5844514 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7326534 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4595392 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4594. Min Act: -0.1700
Data Index: 696941 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4594. Min Act: -0.1700
Data Index: 7618914 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4282. Min Act: -0.1700
Data Index: 2684579 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8344. Min Range: -5.8344
Max Act: 5.4282. Min Act: -0.1700
Data Index: 2460633 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19