Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 565 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.9633. Min Act: -0.1700
Data Index: 529723 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4336278 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.8382. Min Act: -0.1700
Data Index: 3093903 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.8382. Min Act: -0.1700
Data Index: 7564558 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.8070. Min Act: -0.1700
Data Index: 2825634 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.7757. Min Act: -0.1700
Data Index: 7453496 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.7757. Min Act: -0.1700
Data Index: 4596836 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.7913. Min Act: -0.1700
Data Index: 576179 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.7288. Min Act: -0.1700
Data Index: 863399 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.7131. Min Act: -0.1700
Data Index: 2017057 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6662. Min Act: -0.1700
Data Index: 5828138 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6975. Min Act: -0.1700
Data Index: 1110315 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6975. Min Act: -0.1700
Data Index: 3077307 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6818. Min Act: -0.1700
Data Index: 6515007 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6662. Min Act: -0.1700
Data Index: 6832635 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6818. Min Act: -0.1700
Data Index: 1133502 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6662. Min Act: -0.1700
Data Index: 4354532 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6349. Min Act: -0.1700
Data Index: 1902020 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6193. Min Act: -0.1700
Data Index: 8346027 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9633. Min Range: -3.9633
Max Act: 3.6349. Min Act: -0.1700
Data Index: 2718663 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19