Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.8925. Min Act: -0.1700
Data Index: 646744 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6737. Min Act: -0.1700
Data Index: 527863 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.7050. Min Act: -0.1700
Data Index: 8649268 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6737. Min Act: -0.1700
Data Index: 7773015 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.7050. Min Act: -0.1700
Data Index: 789643 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6425. Min Act: -0.1700
Data Index: 1081691 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6425. Min Act: -0.1700
Data Index: 5290218 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6425. Min Act: -0.1700
Data Index: 5210577 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6112. Min Act: -0.1700
Data Index: 771247 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.6425. Min Act: -0.1700
Data Index: 5354072 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.5175. Min Act: -0.1700
Data Index: 6556335 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.5175. Min Act: -0.1700
Data Index: 3276890 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.5175. Min Act: -0.1700
Data Index: 6802279 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.4862. Min Act: -0.1700
Data Index: 6405829 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.4550. Min Act: -0.1700
Data Index: 6643194 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.4237. Min Act: -0.1700
Data Index: 8826821 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.4237. Min Act: -0.1700
Data Index: 3477455 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.3925. Min Act: -0.1700
Data Index: 8559292 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.3925. Min Act: -0.1700
Data Index: 7287519 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8925. Min Range: -6.8925
Max Act: 6.3612. Min Act: -0.1700
Data Index: 961337 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19