Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.6097. Min Act: -0.1700
Data Index: 5948875 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.4847. Min Act: -0.1700
Data Index: 6444881 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.3597. Min Act: -0.1700
Data Index: 6520026 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.2347. Min Act: -0.1700
Data Index: 7834746 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.2972. Min Act: -0.1700
Data Index: 6819288 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.1722. Min Act: -0.1700
Data Index: 6763881 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.0472. Min Act: -0.1700
Data Index: 2869999 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.9847. Min Act: -0.1700
Data Index: 3256537 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.9847. Min Act: -0.1700
Data Index: 2104185 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6097. Min Range: -9.6097
Max Act: 9.0472. Min Act: -0.1700
Data Index: 6763882 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.9222. Min Act: -0.1700
Data Index: 3009129 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.9222. Min Act: -0.1700
Data Index: 2724383 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.8597. Min Act: -0.1700
Data Index: 928314 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.9222. Min Act: -0.1700
Data Index: 5024817 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.7972. Min Act: -0.1700
Data Index: 3039084 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.7972. Min Act: -0.1700
Data Index: 3196338 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.6722. Min Act: -0.1700
Data Index: 2100522 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.6722. Min Act: -0.1700
Data Index: 5179847 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.6722. Min Act: -0.1700
Data Index: 5084985 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6097. Min Range: -9.6097
Max Act: 8.6097. Min Act: -0.1700
Data Index: 4739076 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19