Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1709. Min Act: -0.1700
Data Index: 2678501 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1084. Min Act: -0.1700
Data Index: 1347633 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1084. Min Act: -0.1700
Data Index: 6517142 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.1084. Min Act: -0.1700
Data Index: 7698694 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0147. Min Act: -0.1700
Data Index: 7922077 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0147. Min Act: -0.1700
Data Index: 937058 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1709. Min Range: -5.1709
Max Act: 5.0147. Min Act: -0.1700
Data Index: 7283120 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9522. Min Act: -0.1700
Data Index: 3736531 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9522. Min Act: -0.1700
Data Index: 2898279 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 3703542 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 2968871 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.9209. Min Act: -0.1700
Data Index: 6106250 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8897. Min Act: -0.1700
Data Index: 133572 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8897. Min Act: -0.1700
Data Index: 4547985 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 823414 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4656581 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8897. Min Act: -0.1700
Data Index: 6523465 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8272. Min Act: -0.1700
Data Index: 3560794 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8584. Min Act: -0.1700
Data Index: 5979797 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1709. Min Range: -5.1709
Max Act: 4.8272. Min Act: -0.1700
Data Index: 1027753 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19