Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.6502. Min Act: -0.1700
Data Index: 2452567 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.5877. Min Act: -0.1700
Data Index: 7730102 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.5564. Min Act: -0.1700
Data Index: 3719042 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.5564. Min Act: -0.1700
Data Index: 287782 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.4939. Min Act: -0.1700
Data Index: 8298902 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.5252. Min Act: -0.1700
Data Index: 5740954 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.4939. Min Act: -0.1700
Data Index: 4756127 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.4002. Min Act: -0.1700
Data Index: 3115227 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3689. Min Act: -0.1700
Data Index: 7560069 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3689. Min Act: -0.1700
Data Index: 7189951 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3689. Min Act: -0.1700
Data Index: 5666081 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3377. Min Act: -0.1700
Data Index: 8528502 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3689. Min Act: -0.1700
Data Index: 7588410 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3689. Min Act: -0.1700
Data Index: 235202 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3064. Min Act: -0.1700
Data Index: 721471 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3064. Min Act: -0.1700
Data Index: 6983262 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.3064. Min Act: -0.1700
Data Index: 1943452 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.2752. Min Act: -0.1700
Data Index: 2171750 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.2752. Min Act: -0.1700
Data Index: 619263 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6502. Min Range: -6.6502
Max Act: 6.2752. Min Act: -0.1700
Data Index: 2508980 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19