Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1261 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.4413. Min Act: -0.1700
Data Index: 1415631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.4725. Min Act: -0.1700
Data Index: 5651720 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.3475. Min Act: -0.1700
Data Index: 8529777 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3296208 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.2538. Min Act: -0.1700
Data Index: 1415630 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.1913. Min Act: -0.1700
Data Index: 7444329 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.1913. Min Act: -0.1700
Data Index: 1415633 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5763482 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.1600. Min Act: -0.1700
Data Index: 2679825 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.1288. Min Act: -0.1700
Data Index: 349176 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0975. Min Act: -0.1700
Data Index: 5859990 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0350. Min Act: -0.1700
Data Index: 4093511 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0663. Min Act: -0.1700
Data Index: 7462157 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0663. Min Act: -0.1700
Data Index: 6481286 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0038. Min Act: -0.1700
Data Index: 3110565 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0038. Min Act: -0.1700
Data Index: 2749226 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4725. Min Range: -5.4725
Max Act: 5.0038. Min Act: -0.1700
Data Index: 1939039 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4725. Min Range: -5.4725
Max Act: 4.9725. Min Act: -0.1700
Data Index: 3183451 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4725. Min Range: -5.4725
Max Act: 4.9413. Min Act: -0.1700
Data Index: 7954126 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4725. Min Range: -5.4725
Max Act: 4.9413. Min Act: -0.1700
Data Index: 7181310 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19