Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 518 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.7510. Min Act: -0.1700
Data Index: 267171 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.7510. Min Act: -0.1700
Data Index: 5439904 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.7510. Min Act: -0.1700
Data Index: 4419352 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.6573. Min Act: -0.1700
Data Index: 5066680 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.6573. Min Act: -0.1700
Data Index: 4273606 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.5323. Min Act: -0.1700
Data Index: 2804227 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.5010. Min Act: -0.1700
Data Index: 6630542 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.5010. Min Act: -0.1700
Data Index: 1332784 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.4385. Min Act: -0.1700
Data Index: 6630540 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3760. Min Act: -0.1700
Data Index: 5442044 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3760. Min Act: -0.1700
Data Index: 4273607 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3760. Min Act: -0.1700
Data Index: 6495291 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3448. Min Act: -0.1700
Data Index: 1535488 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.2823. Min Act: -0.1700
Data Index: 3625463 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3448. Min Act: -0.1700
Data Index: 7189752 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3135. Min Act: -0.1700
Data Index: 202686 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3135. Min Act: -0.1700
Data Index: 7641271 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.3135. Min Act: -0.1700
Data Index: 4612938 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.2823. Min Act: -0.1700
Data Index: 7143863 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7510. Min Range: -4.7510
Max Act: 4.2823. Min Act: -0.1700
Data Index: 6700027 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19