Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4185 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.8866. Min Act: -0.1700
Data Index: 3490564 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7929. Min Act: -0.1700
Data Index: 5172619 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7929. Min Act: -0.1700
Data Index: 6763110 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7929. Min Act: -0.1700
Data Index: 1664983 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7616. Min Act: -0.1700
Data Index: 3781981 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7616. Min Act: -0.1700
Data Index: 4279963 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7304. Min Act: -0.1699
Data Index: 4344068 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7616. Min Act: -0.1700
Data Index: 524097 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7304. Min Act: -0.1700
Data Index: 4859695 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7304. Min Act: -0.1700
Data Index: 477152 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.7304. Min Act: -0.1700
Data Index: 5015994 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.6366. Min Act: -0.1700
Data Index: 4215059 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.6679. Min Act: -0.1700
Data Index: 4841341 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.6054. Min Act: -0.1700
Data Index: 3965724 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.6054. Min Act: -0.1700
Data Index: 5823158 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.5741. Min Act: -0.1700
Data Index: 4975328 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.5429. Min Act: -0.1700
Data Index: 1632067 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.5429. Min Act: -0.1700
Data Index: 3130056 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.5429. Min Act: -0.1700
Data Index: 5214973 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8866. Min Range: -6.8866
Max Act: 6.5116. Min Act: -0.1700
Data Index: 2065877 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19