Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2715 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.7393. Min Act: -0.1700
Data Index: 566432 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.7080. Min Act: -0.1700
Data Index: 4198045 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.6768. Min Act: -0.1700
Data Index: 6240385 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.6455. Min Act: -0.1700
Data Index: 382621 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.5205. Min Act: -0.1700
Data Index: 1106778 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.5205. Min Act: -0.1700
Data Index: 7710985 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3643. Min Act: -0.1700
Data Index: 513585 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3643. Min Act: -0.1700
Data Index: 5989980 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3643. Min Act: -0.1700
Data Index: 3556936 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3018. Min Act: -0.1700
Data Index: 5730877 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3018. Min Act: -0.1700
Data Index: 2425773 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2705. Min Act: -0.1700
Data Index: 1861764 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3018. Min Act: -0.1700
Data Index: 4676694 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.3018. Min Act: -0.1700
Data Index: 8714521 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2705. Min Act: -0.1700
Data Index: 1463911 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2705. Min Act: -0.1700
Data Index: 1814217 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2705. Min Act: -0.1700
Data Index: 8458989 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2705. Min Act: -0.1700
Data Index: 8259363 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2393. Min Act: -0.1700
Data Index: 4454142 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7393. Min Range: -5.7393
Max Act: 5.2393. Min Act: -0.1700
Data Index: 8783731 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19