Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2716 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.4521. Min Act: -0.1700
Data Index: 3681571 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 6667469 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4038774 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 4811222 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2958. Min Act: -0.1700
Data Index: 5679819 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.3271. Min Act: -0.1700
Data Index: 8483785 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 4547234 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 3206307 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 738347 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 6364060 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 6236802 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2646. Min Act: -0.1700
Data Index: 53701 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 1010319 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1882637 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2333. Min Act: -0.1700
Data Index: 336236 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 11988 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 8797514 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.2021. Min Act: -0.1700
Data Index: 6733658 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1708. Min Act: -0.1700
Data Index: 2370442 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4521. Min Range: -5.4521
Max Act: 5.1396. Min Act: -0.1700
Data Index: 4059682 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19