Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.9436. Min Act: -0.1700
Data Index: 5121066 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.7249. Min Act: -0.1700
Data Index: 3449843 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.7249. Min Act: -0.1700
Data Index: 2357565 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.6311. Min Act: -0.1700
Data Index: 1143681 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.5999. Min Act: -0.1700
Data Index: 1211241 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.5686. Min Act: -0.1700
Data Index: 2637375 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.5686. Min Act: -0.1700
Data Index: 4089559 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4749. Min Act: -0.1700
Data Index: 8143236 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4749. Min Act: -0.1700
Data Index: 2339071 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4749. Min Act: -0.1700
Data Index: 7885600 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4436. Min Act: -0.1700
Data Index: 7517144 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4124. Min Act: -0.1700
Data Index: 474499 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4124. Min Act: -0.1700
Data Index: 3005464 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4124. Min Act: -0.1700
Data Index: 6307356 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.3811. Min Act: -0.1700
Data Index: 4807709 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.4124. Min Act: -0.1700
Data Index: 5388160 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.3811. Min Act: -0.1700
Data Index: 7911097 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.3811. Min Act: -0.1700
Data Index: 8331369 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.3499. Min Act: -0.1700
Data Index: 90757 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9436. Min Range: -5.9436
Max Act: 5.3499. Min Act: -0.1700
Data Index: 4334720 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19